{"id":1568,"date":"2023-08-16T17:12:13","date_gmt":"2023-08-16T17:12:13","guid":{"rendered":"https:\/\/www.gptmain.news\/?p=1568"},"modified":"2023-08-16T17:12:13","modified_gmt":"2023-08-16T17:12:13","slug":"%d1%80%d0%b0%d1%81%d0%bf%d1%83%d1%82%d0%b0%d1%82%d1%8c-%d0%b3%d1%80%d0%b0%d0%b4%d0%b8%d0%b5%d0%bd%d1%82%d1%8b-%d0%bf%d0%be%d0%bb%d0%b8%d1%82%d0%b8%d0%ba%d0%b8-%d0%b8-%d1%83%d0%ba%d1%80%d0%b5%d0%bf","status":"publish","type":"post","link":"https:\/\/gptmain.news\/?p=1568","title":{"rendered":"\u0420\u0430\u0441\u043f\u0443\u0442\u0430\u0442\u044c \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u044b \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0438 \u0423\u041a\u0420\u0415\u041f\u0418\u0422\u042c\n | GPTMain News"},"content":{"rendered":"<div id=\"\">\n<p>\u041d\u0430 \u044d\u0442\u043e\u0442 \u0440\u0430\u0437 \u043c\u044b \u0441\u043e\u0431\u0438\u0440\u0430\u0435\u043c\u0441\u044f \u0437\u0430\u043d\u044f\u0442\u044c \u0441\u0435\u0431\u044f \u0434\u0440\u0443\u0433\u0438\u043c \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u043e\u043c \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u043e\u0432 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c, \u043d\u0430\u0437\u044b\u0432\u0430\u0435\u043c\u044b\u0445 \u043c\u0435\u0442\u043e\u0434\u0430\u043c\u0438, \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u043d\u044b\u043c\u0438 \u043d\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0435.  \u0415\u0441\u043b\u0438 \u0432\u044b \u043f\u043e\u043c\u043d\u0438\u0442\u0435, \u0435\u0441\u0442\u044c \u0434\u0432\u0435 \u043e\u0441\u043d\u043e\u0432\u043d\u044b\u0435 \u0433\u0440\u0443\u043f\u043f\u044b \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c \u0431\u0435\u0437 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439.<\/p>\n<p>\u041c\u044b \u0430\u043d\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u043f\u0435\u0440\u0432\u044b\u0435 \u0432 \u0434\u0432\u0443\u0445 \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0438\u0445 \u0441\u0442\u0430\u0442\u044c\u044f\u0445, \u0433\u0434\u0435 \u043c\u044b \u0433\u043e\u0432\u043e\u0440\u0438\u043b\u0438 \u043e Q-learning \u0438 Deep Q Networks, \u0430 \u0442\u0430\u043a\u0436\u0435 \u043e \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0445 \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f\u0445 \u0431\u0430\u0437\u043e\u0432\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439, \u0442\u0430\u043a\u0438\u0445 \u043a\u0430\u043a Double Deep Q Networks \u0438 Prioritized Replay.  \u041f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u0442\u0435 \u0438\u0445 \u0437\u0434\u0435\u0441\u044c \u0438 \u0437\u0434\u0435\u0441\u044c.<\/p>\n<p>\u0414\u0430\u0432\u0430\u0439\u0442\u0435 \u0441\u0434\u0435\u043b\u0430\u0435\u043c \u0431\u044b\u0441\u0442\u0440\u0443\u044e \u043f\u0435\u0440\u0435\u043c\u043e\u0442\u043a\u0443.  \u041f\u043e\u043c\u043d\u0438\u0442\u0435, \u0447\u0442\u043e \u043c\u044b \u0444\u043e\u0440\u043c\u0443\u043b\u0438\u0440\u0443\u0435\u043c \u043d\u0430\u0448\u0438 \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u044b \u043a\u0430\u043a \u043c\u0430\u0440\u043a\u043e\u0432\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u044b \u043f\u0440\u0438\u043d\u044f\u0442\u0438\u044f \u0440\u0435\u0448\u0435\u043d\u0438\u0439 \u0438 \u0447\u0442\u043e \u043d\u0430\u0448\u0430 \u0446\u0435\u043b\u044c \u2014 \u043d\u0430\u0439\u0442\u0438 \u043d\u0430\u0438\u043b\u0443\u0447\u0448\u0443\u044e \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0443, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u043e\u0442\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0435\u043c \u0441\u043e\u0441\u0442\u043e\u044f\u043d\u0438\u0439 \u0432 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f.  \u0414\u0440\u0443\u0433\u0438\u043c\u0438 \u0441\u043b\u043e\u0432\u0430\u043c\u0438, \u043c\u044b \u0445\u043e\u0442\u0438\u043c \u0437\u043d\u0430\u0442\u044c, \u043a\u0430\u043a\u043e\u0432\u043e \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0435 \u0441 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u044b\u043c \u043e\u0436\u0438\u0434\u0430\u0435\u043c\u044b\u043c \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0435\u043c \u0432 \u0434\u0430\u043d\u043d\u043e\u043c \u0441\u043e\u0441\u0442\u043e\u044f\u043d\u0438\u0438.  \u0412 \u043c\u0435\u0442\u043e\u0434\u0430\u0445, \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u043d\u044b\u0445 \u043d\u0430 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f\u0445, \u043c\u044b \u0434\u043e\u0441\u0442\u0438\u0433\u0430\u0435\u043c \u044d\u0442\u043e\u0433\u043e, \u043d\u0430\u0445\u043e\u0434\u044f \u0438\u043b\u0438 \u0430\u043f\u043f\u0440\u043e\u043a\u0441\u0438\u043c\u0438\u0440\u0443\u044f \u0444\u0443\u043d\u043a\u0446\u0438\u044e \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f, \u0430 \u0437\u0430\u0442\u0435\u043c \u0438\u0437\u0432\u043b\u0435\u043a\u0430\u044f \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0443.  \u0427\u0442\u043e, \u0435\u0441\u043b\u0438 \u043c\u044b \u043f\u043e\u043b\u043d\u043e\u0441\u0442\u044c\u044e \u043e\u0442\u0431\u0440\u043e\u0441\u0438\u043c \u0446\u0435\u043d\u043d\u043e\u0441\u0442\u043d\u0443\u044e \u0447\u0430\u0441\u0442\u044c \u0438 \u043d\u0430\u0439\u0434\u0435\u043c \u043d\u0435\u043f\u043e\u0441\u0440\u0435\u0434\u0441\u0442\u0432\u0435\u043d\u043d\u043e \u041f\u043e\u043b\u0438\u0442\u0438\u043a\u0443.  \u042d\u0442\u043e \u0442\u043e, \u0447\u0442\u043e \u0434\u0435\u043b\u0430\u044e\u0442 \u043c\u0435\u0442\u043e\u0434\u044b, \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u043d\u044b\u0435 \u043d\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0435.<\/p>\n<p>\u041d\u0435 \u043f\u043e\u0439\u043c\u0438\u0442\u0435 \u043c\u0435\u043d\u044f \u043d\u0435\u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u043e.  \u0421\u0435\u0442\u0438 Q-learning \u0438 Deep Q \u0432\u0435\u043b\u0438\u043a\u043e\u043b\u0435\u043f\u043d\u044b, \u0438 \u043e\u043d\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442\u0441\u044f \u0432\u043e \u043c\u043d\u043e\u0433\u0438\u0445 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f\u0445, \u043d\u043e \u043c\u0435\u0442\u043e\u0434\u044b, \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u043d\u044b\u0435 \u043d\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0435, \u043f\u0440\u0435\u0434\u043b\u0430\u0433\u0430\u044e\u0442 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0434\u0440\u0443\u0433\u0438\u0445 \u043f\u0440\u0435\u0438\u043c\u0443\u0449\u0435\u0441\u0442\u0432:<\/p>\n<ul>\n<li>\n<p>\u041e\u043d\u0438 \u043b\u0435\u0433\u0447\u0435 \u0441\u0445\u043e\u0434\u044f\u0442\u0441\u044f \u043a \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u043e\u043c\u0443 \u0438\u043b\u0438 \u0433\u043b\u043e\u0431\u0430\u043b\u044c\u043d\u043e\u043c\u0443 \u043c\u0430\u043a\u0441\u0438\u043c\u0443\u043c\u0443 \u0438 \u043d\u0435 \u043f\u043e\u0434\u0432\u0435\u0440\u0436\u0435\u043d\u044b \u043e\u0441\u0446\u0438\u043b\u043b\u044f\u0446\u0438\u044f\u043c.<\/p>\n<\/li>\n<li>\n<p>\u041e\u043d\u0438 \u043e\u0447\u0435\u043d\u044c \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u044b \u0432 \u043c\u043d\u043e\u0433\u043e\u043c\u0435\u0440\u043d\u044b\u0445 \u0438\u043b\u0438 <strong>\u043d\u0435\u043f\u0440\u0435\u0440\u044b\u0432\u043d\u044b\u0439<\/strong> \u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u0441\u0442\u0432\u0430<\/p>\n<\/li>\n<li>\n<p>\u041e\u043d\u0438 \u043c\u043e\u0433\u0443\u0442 \u0443\u0447\u0438\u0442\u044c\u0441\u044f <strong>\u0441\u0442\u043e\u0445\u0430\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0439<\/strong> \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 (\u0441\u0442\u043e\u0445\u0430\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0434\u0430\u044e\u0442<br \/>\n<strong>\u0440\u0430\u0441\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u0435 \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e\u0441\u0442\u0435\u0439<\/strong> \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f, \u0430 \u043d\u0435 \u0434\u0435\u0442\u0435\u0440\u043c\u0438\u043d\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u043e\u0435 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0435.  \u041e\u043d\u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0438 \u0432 \u0441\u0442\u043e\u0445\u0430\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0440\u0435\u0434\u0430\u0445, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043e\u043d\u0438 \u0441\u043c\u043e\u0434\u0435\u043b\u0438\u0440\u043e\u0432\u0430\u043b\u0438 \u043a\u0430\u043a \u0447\u0430\u0441\u0442\u0438\u0447\u043d\u043e \u043d\u0430\u0431\u043b\u044e\u0434\u0430\u0435\u043c\u044b\u0435 \u043c\u0430\u0440\u043a\u043e\u0432\u0441\u043a\u0438\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441\u044b \u043f\u0440\u0438\u043d\u044f\u0442\u0438\u044f \u0440\u0435\u0448\u0435\u043d\u0438\u0439, \u0433\u0434\u0435 \u043c\u044b \u0442\u043e\u0447\u043d\u043e \u043d\u0435 \u0437\u043d\u0430\u0435\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f)<\/p>\n<\/li>\n<\/ul>\n<p>\u041f\u043e\u0434\u043e\u0436\u0434\u0438 \u043c\u0438\u043d\u0443\u0442\u043a\u0443.  \u042f \u0433\u043e\u0432\u043e\u0440\u0438\u043b \u043e \u0441\u0445\u043e\u0434\u0438\u043c\u043e\u0441\u0442\u0438, \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u043e\u043c \u043c\u0430\u043a\u0441\u0438\u043c\u0443\u043c\u0435, \u043d\u0435\u043f\u0440\u0435\u0440\u044b\u0432\u043d\u043e\u043c \u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u0441\u0442\u0432\u0435, \u0441\u0442\u043e\u0445\u0430\u0441\u0442\u0438\u0447\u043d\u043e\u0441\u0442\u0438.  \u0427\u0442\u043e \u0437\u0434\u0435\u0441\u044c \u043f\u0440\u043e\u0438\u0441\u0445\u043e\u0434\u0438\u0442?<\/p>\n<p>\u041d\u0443, \u0434\u0435\u043b\u043e \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e <strong>\u041e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c, \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u043d\u043e\u0435 \u043d\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0435, \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u043e\u0439 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438.<\/strong> \u041d\u043e \u0447\u0442\u043e \u044d\u0442\u043e \u0437\u043d\u0430\u0447\u0438\u0442?<\/p>\n<p>\u0423 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0430 (\u03c0) \u0441 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u043c\u0438 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0430\u043c\u0438 \u0442\u0435\u0442\u0430 (\u03b8), \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0432\u044b\u0432\u043e\u0434\u0438\u0442 \u0440\u0430\u0441\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u0435 \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e\u0441\u0442\u0435\u0439 \u043f\u043e \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f\u043c.  \u041c\u044b \u0445\u043e\u0442\u0438\u043c \u043d\u0430\u0439\u0442\u0438 \u043d\u0430\u0438\u043b\u0443\u0447\u0448\u0443\u044e \u0442\u0435\u0442\u0443, \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442 \u043d\u0430\u0438\u043b\u0443\u0447\u0448\u0443\u044e \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0443.  \u041d\u043e \u043a\u0430\u043a \u043c\u044b \u043e\u0446\u0435\u043d\u0438\u0432\u0430\u0435\u043c, \u0445\u043e\u0440\u043e\u0448\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0430 \u0438\u043b\u0438 \u043f\u043b\u043e\u0445\u0430?  \u041c\u044b \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c \u0446\u0435\u043b\u0435\u0432\u0443\u044e \u0444\u0443\u043d\u043a\u0446\u0438\u044e \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 J(\u03b8), \u043a\u043e\u0442\u043e\u0440\u0430\u044f \u0447\u0430\u0449\u0435 \u0432\u0441\u0435\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u0435\u0442 \u0441\u043e\u0431\u043e\u0439 \u043e\u0436\u0438\u0434\u0430\u0435\u043c\u043e\u0435 \u043d\u0430\u043a\u043e\u043f\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0435 \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0435.  \u041a\u0440\u043e\u043c\u0435 \u0442\u043e\u0433\u043e, \u0446\u0435\u043b\u0435\u0432\u0430\u044f \u0444\u0443\u043d\u043a\u0446\u0438\u044f \u0440\u0430\u0437\u043b\u0438\u0447\u0430\u0435\u0442\u0441\u044f \u0432 \u0437\u0430\u0432\u0438\u0441\u0438\u043c\u043e\u0441\u0442\u0438 \u043e\u0442 \u0442\u043e\u0433\u043e, \u0438\u043c\u0435\u0435\u043c \u043b\u0438 \u043c\u044b \u044d\u043f\u0438\u0437\u043e\u0434\u0438\u0447\u0435\u0441\u043a\u0443\u044e \u0438\u043b\u0438 \u043f\u0440\u043e\u0434\u043e\u043b\u0436\u0430\u044e\u0449\u0443\u044e\u0441\u044f \u0441\u0440\u0435\u0434\u0443.<\/p>\n<div class=\"math\"><span class=\"katex-display\"><span class=\"katex\"><span class=\"katex-mathml\"><math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"block\"><semantics><mrow><msub><mi>\u03c0<\/mi><mi>\u03b8<\/mi><\/msub><mo stretchy=\"false\">(<\/mo><mi>\u0430<\/mi><mi mathvariant=\"normal\">\u2223<\/mi><mi>\u0441<\/mi><mo stretchy=\"false\">)<\/mo><mo>&#8220;=&#8221;<\/mo><mi>\u043f<\/mi><mo stretchy=\"false\">[<\/mo><mi>a<\/mi><mi mathvariant=\"normal\">\u2223<\/mi><mi>s<\/mi><mo stretchy=\"false\">]<\/mo><\/mrow><annotation encoding=\"application\/x-tex\">\\\u043f\u0438 _ {\\ \u0442\u0435\u0442\u0430} (\u0430 | \u0441) = \u0420[a | s]<\/annotation><\/semantics><\/math><\/span><span class=\"katex-html\" aria-hidden=\"true\"><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em\"\/><span class=\"mord\"><span class=\"mord mathnormal\" style=\"margin-right:0.03588em\">\u03c0<\/span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.33610799999999996em\"><span style=\"top:-2.5500000000000003em;margin-left:-0.03588em;margin-right:0.05em\"><span class=\"pstrut\" style=\"height:2.7em\"\/><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mathnormal mtight\" style=\"margin-right:0.02778em\">\u03b8<\/span><\/span><\/span><\/span><\/span><span class=\"vlist-s\">\u200b<\/span><\/span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em\"><span\/><\/span><\/span><\/span><\/span><\/span><span class=\"mopen\">(<\/span><span class=\"mord mathnormal\">\u0430<\/span><span class=\"mord\">\u2223<\/span><span class=\"mord mathnormal\">\u0441<\/span><span class=\"mclose\">)<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><span class=\"mrel\">&#8220;=&#8221;<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><\/span><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.13889em\">\u043f<\/span><span class=\"mopen\">[<\/span><span class=\"mord mathnormal\">a<\/span><span class=\"mord\">\u2223<\/span><span class=\"mord mathnormal\">s<\/span><span class=\"mclose\">]<\/span><\/span><\/span><\/span><\/span><\/div>\n<div class=\"math\"><span class=\"katex-display\"><span class=\"katex\"><span class=\"katex-mathml\"><math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"block\"><semantics><mrow><mi>\u0414\u0436<\/mi><mo stretchy=\"false\">(<\/mo><mi>\u03b8<\/mi><mo stretchy=\"false\">)<\/mo><mo>&#8220;=&#8221;<\/mo><msub><mi>\u0415<\/mi><mrow><mi>\u03c0<\/mi><mi>\u03b8<\/mi><\/mrow><\/msub><mrow><mo fence=\"true\">[<\/mo><mo>\u2211<\/mo><mi>\u03b3<\/mi><mi>r<\/mi><mo fence=\"true\">]<\/mo><\/mrow><\/mrow><annotation encoding=\"application\/x-tex\">J (\\ \u0442\u0435\u0442\u0430) = E _ {\\ \u043f\u0438 \\ \u0442\u0435\u0442\u0430} \\ \u0432\u043b\u0435\u0432\u043e[\\sum \\gamma r\\right]<\/annotation><\/semantics><\/math><\/span><span class=\"katex-html\" aria-hidden=\"true\"><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.09618em\">\u0414\u0436<\/span><span class=\"mopen\">(<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">\u03b8<\/span><span class=\"mclose\">)<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><span class=\"mrel\">&#8220;=&#8221;<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><\/span><span class=\"base\"><span class=\"strut\" style=\"height:1.80002em;vertical-align:-0.65002em\"\/><span class=\"mord\"><span class=\"mord mathnormal\" style=\"margin-right:0.05764em\">\u0415<\/span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.33610799999999996em\"><span style=\"top:-2.5500000000000003em;margin-left:-0.05764em;margin-right:0.05em\"><span class=\"pstrut\" style=\"height:2.7em\"\/><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mathnormal mtight\" style=\"margin-right:0.03588em\">\u03c0<\/span><span class=\"mord mathnormal mtight\" style=\"margin-right:0.02778em\">\u03b8<\/span><\/span><\/span><\/span><\/span><span class=\"vlist-s\">\u200b<\/span><\/span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em\"><span\/><\/span><\/span><\/span><\/span><\/span><span class=\"mspace\" style=\"margin-right:0.16666666666666666em\"\/><span class=\"minner\"><span class=\"mopen delimcenter\" style=\"top:0em\"><span class=\"delimsizing size2\">[<\/span><\/span><span class=\"mop op-symbol large-op\" style=\"position:relative;top:-0.000004999999999977245em\">\u2211<\/span><span class=\"mspace\" style=\"margin-right:0.16666666666666666em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.05556em\">\u03b3<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">r<\/span><span class=\"mclose delimcenter\" style=\"top:0em\"><span class=\"delimsizing size2\">]<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/div>\n<p>\u0418\u0442\u0430\u043a, \u043c\u044b \u0437\u0434\u0435\u0441\u044c, \u0441 \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u043e\u0439 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438 \u0432 \u043d\u0430\u0448\u0438\u0445 \u0440\u0443\u043a\u0430\u0445.  \u0412\u0441\u0435, \u0447\u0442\u043e \u043d\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u0441\u0434\u0435\u043b\u0430\u0442\u044c, \u044d\u0442\u043e \u043d\u0430\u0439\u0442\u0438 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0442\u0435\u0442\u0430 (\u03b8), \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u0430\u043a\u0441\u0438\u043c\u0438\u0437\u0438\u0440\u0443\u044e\u0442 J (\u03b8), \u0438 \u0443 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0430.<\/p>\n<p>\u041f\u0435\u0440\u0432\u044b\u0439 \u043f\u043e\u0434\u0445\u043e\u0434 \u0437\u0430\u043a\u043b\u044e\u0447\u0430\u0435\u0442\u0441\u044f \u0432 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0438 \u043c\u0435\u0442\u043e\u0434\u0430 \u0433\u0440\u0443\u0431\u043e\u0439 \u0441\u0438\u043b\u044b \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0435 \u0432\u0441\u0435\u0433\u043e \u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u0441\u0442\u0432\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438.  \u0425\u043c, \u043d\u0435 \u0442\u0430\u043a \u0445\u043e\u0440\u043e\u0448\u043e.<\/p>\n<p>\u0412\u0442\u043e\u0440\u043e\u0439 \u043f\u043e\u0434\u0445\u043e\u0434 \u0437\u0430\u043a\u043b\u044e\u0447\u0430\u0435\u0442\u0441\u044f \u0432 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0438 \u043f\u0440\u044f\u043c\u043e\u0433\u043e \u043f\u043e\u0438\u0441\u043a\u0430 \u0432 \u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u0441\u0442\u0432\u0435 \u043f\u043e\u043b\u0438\u0442\u0438\u043a \u0438\u043b\u0438 \u0435\u0433\u043e \u043f\u043e\u0434\u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u0435.  \u0418 \u0437\u0434\u0435\u0441\u044c \u043c\u044b \u0432\u0432\u043e\u0434\u0438\u043c \u0442\u0435\u0440\u043c\u0438\u043d <strong>\u041f\u043e\u0438\u0441\u043a \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438.<\/strong> \u041d\u0430 \u0441\u0430\u043c\u043e\u043c \u0434\u0435\u043b\u0435 \u0435\u0441\u0442\u044c \u0434\u0432\u0430 \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u0430 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u043e\u0432, \u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c.  \u041d\u0430\u0437\u043e\u0432\u0435\u043c \u0438\u0445:<\/p>\n<ul>\n<li>\n<p>\u0413\u0440\u0430\u0434\u0438\u0435\u043d\u0442 \u0431\u0435\u0441\u043f\u043b\u0430\u0442\u043d\u043e<\/p>\n<\/li>\n<li>\n<p>\u0413\u0440\u0430\u0434\u0438\u0435\u043d\u0442 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435<\/p>\n<\/li>\n<\/ul>\n<p>\u041f\u043e\u0434\u0443\u043c\u0430\u0439\u0442\u0435 \u043e \u043b\u044e\u0431\u043e\u043c \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0435, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0432\u044b \u043a\u043e\u0433\u0434\u0430-\u043b\u0438\u0431\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043b\u0438 \u0434\u043b\u044f \u0440\u0435\u0448\u0435\u043d\u0438\u044f \u0437\u0430\u0434\u0430\u0447\u0438 \u043e\u043f\u0442\u0438\u043c\u0438\u0437\u0430\u0446\u0438\u0438, \u0432 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442\u0441\u044f \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u043d\u044b\u0435.  \u042d\u0442\u043e \u0431\u0435\u0437\u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u044b\u0439 \u043c\u0435\u0442\u043e\u0434, \u0438 \u0431\u043e\u043b\u044c\u0448\u0438\u043d\u0441\u0442\u0432\u043e \u0438\u0437 \u043d\u0438\u0445 \u043c\u043e\u0436\u043d\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0432 \u043d\u0430\u0448\u0435\u043c \u0441\u043b\u0443\u0447\u0430\u0435.  \u0412\u043e\u0442 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u043f\u0440\u0438\u043c\u0435\u0440\u044b:<\/p>\n<ul>\n<li>\n<p>\u0412\u043e\u0441\u0445\u043e\u0436\u0434\u0435\u043d\u0438\u0435 \u043d\u0430 \u0445\u043e\u043b\u043c \u2014 \u044d\u0442\u043e \u0441\u043b\u0443\u0447\u0430\u0439\u043d\u044b\u0439 \u0438\u0442\u0435\u0440\u0430\u0442\u0438\u0432\u043d\u044b\u0439 \u043b\u043e\u043a\u0430\u043b\u044c\u043d\u044b\u0439 \u043f\u043e\u0438\u0441\u043a.<\/p>\n<\/li>\n<li>\n<p>\u0421\u0438\u043c\u043f\u043b\u0435\u043a\u0441: \u043f\u043e\u043f\u0443\u043b\u044f\u0440\u043d\u044b\u0439 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c \u043b\u0438\u043d\u0435\u0439\u043d\u043e\u0433\u043e \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f (\u0435\u0441\u043b\u0438 \u0432\u044b \u043a\u043e\u043f\u0430\u0435\u0442\u0435\u0441\u044c \u0432 \u043b\u0438\u043d\u0435\u0439\u043d\u043e\u0439 \u0430\u043b\u0433\u0435\u0431\u0440\u0435, \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0438\u0442\u0435 \u0435\u0433\u043e)<\/p>\n<\/li>\n<li>\n<p>\u0418\u043c\u0438\u0442\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0439 \u043e\u0442\u0436\u0438\u0433, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u043f\u0435\u0440\u0435\u043c\u0435\u0449\u0430\u0435\u0442\u0441\u044f \u043c\u0435\u0436\u0434\u0443 \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u043c\u0438 \u0441\u043e\u0441\u0442\u043e\u044f\u043d\u0438\u044f\u043c\u0438 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u043e\u0439 \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e\u0441\u0442\u0438.<\/p>\n<\/li>\n<li>\n<p>\u042d\u0432\u043e\u043b\u044e\u0446\u0438\u043e\u043d\u043d\u044b\u0435 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b, \u043c\u043e\u0434\u0435\u043b\u0438\u0440\u0443\u044e\u0449\u0438\u0435 \u043f\u0440\u043e\u0446\u0435\u0441\u0441 \u0444\u0438\u0437\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u044d\u0432\u043e\u043b\u044e\u0446\u0438\u0438.  \u041e\u043d\u0438 \u043d\u0430\u0447\u0438\u043d\u0430\u044e\u0442 \u0441\u043e \u0441\u043b\u0443\u0447\u0430\u0439\u043d\u043e\u0433\u043e \u0441\u043e\u0441\u0442\u043e\u044f\u043d\u0438\u044f, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u043d\u043e\u0433\u043e \u0432 \u0432\u0438\u0434\u0435 \u0433\u0435\u043d\u043e\u043c\u0430, \u0438 \u043f\u0443\u0442\u0435\u043c \u0441\u043a\u0440\u0435\u0449\u0438\u0432\u0430\u043d\u0438\u044f, \u043c\u0443\u0442\u0430\u0446\u0438\u0438 \u0438 \u0444\u0438\u0437\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u043e\u0442\u0431\u043e\u0440\u0430 \u043d\u0430\u0445\u043e\u0434\u044f\u0442 \u0441\u0430\u043c\u043e\u0435 \u0441\u0438\u043b\u044c\u043d\u043e\u0435 \u043f\u043e\u043a\u043e\u043b\u0435\u043d\u0438\u0435 (\u0438\u043b\u0438 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0435 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u0435).  \u0412\u0441\u044f \u043a\u043e\u043d\u0446\u0435\u043f\u0446\u0438\u044f \u00ab\u0412\u044b\u0436\u0438\u0432\u0430\u0435\u0442 \u0441\u0438\u043b\u044c\u043d\u0435\u0439\u0448\u0438\u0439\u00bb, \u0437\u0430\u043a\u043b\u044e\u0447\u0435\u043d\u043d\u0430\u044f \u0432 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c.<\/p>\n<\/li>\n<\/ul>\n<p>\u0412\u0442\u043e\u0440\u043e\u0435 \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u043e \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442 \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u044b\u0439 \u0441\u043f\u0443\u0441\u043a \u0438\u043b\u0438, \u0435\u0441\u043b\u0438 \u0431\u044b\u0442\u044c \u0431\u043e\u043b\u0435\u0435 \u0442\u043e\u0447\u043d\u044b\u043c, \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u044b\u0439 \u043f\u043e\u0434\u044a\u0435\u043c.<\/p>\n<p>\u0412 (\u0432\u0430\u043d\u0438\u043b\u044c\u043d\u043e\u043c) \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u043e\u043c \u0441\u043f\u0443\u0441\u043a\u0435 \u043c\u044b:<\/p>\n<ol>\n<li>\n<p>\u0418\u043d\u0438\u0446\u0438\u0430\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0442\u0435\u0442\u0430<\/p>\n<\/li>\n<li>\n<p>\u0421\u043e\u0437\u0434\u0430\u0442\u044c \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0439 \u044d\u043f\u0438\u0437\u043e\u0434<\/p>\n<\/li>\n<li>\n<p>\u041f\u043e\u043b\u0443\u0447\u0438\u0442\u0435 \u0434\u043e\u043b\u0433\u043e\u0441\u0440\u043e\u0447\u043d\u043e\u0435 \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0435<\/p>\n<\/li>\n<li>\n<p>\u041e\u0431\u043d\u043e\u0432\u0438\u0442\u044c \u0442\u0435\u0442\u0430 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0435 \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u044f \u0437\u0430 \u0432\u0441\u0435 \u0432\u0440\u0435\u043c\u0435\u043d\u043d\u044b\u0435 \u0448\u0430\u0433\u0438<\/p>\n<\/li>\n<li>\n<p>\u041f\u043e\u0432\u0442\u043e\u0440\u0438\u0442\u044c<\/p>\n<\/li>\n<\/ol>\n<p>\u041d\u043e \u0435\u0441\u0442\u044c \u043d\u0435\u0431\u043e\u043b\u044c\u0448\u0430\u044f \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u0430.  \u041c\u043e\u0436\u0435\u043c \u043b\u0438 \u043c\u044b \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u044c \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442 \u0442\u0435\u0442\u0430 \u0432 \u0430\u043d\u0430\u043b\u0438\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u0444\u043e\u0440\u043c\u0435?  \u041f\u043e\u0442\u043e\u043c\u0443 \u0447\u0442\u043e, \u0435\u0441\u043b\u0438 \u043c\u044b \u043d\u0435 \u0441\u043c\u043e\u0436\u0435\u043c, \u0432\u0435\u0441\u044c \u043f\u0440\u043e\u0446\u0435\u0441\u0441 \u043f\u043e\u0439\u0434\u0435\u0442 \u0432 \u043c\u0443\u0441\u043e\u0440\u043a\u0443.  \u041e\u043a\u0430\u0437\u044b\u0432\u0430\u0435\u0442\u0441\u044f, \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u0441 \u043d\u0435\u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u0445\u0438\u0442\u0440\u043e\u0441\u0442\u044c\u044e.  \u041c\u044b \u0434\u043e\u043b\u0436\u043d\u044b \u043f\u0440\u0435\u0434\u043f\u043e\u043b\u043e\u0436\u0438\u0442\u044c, \u0447\u0442\u043e \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0430 \u0434\u0438\u0444\u0444\u0435\u0440\u0435\u043d\u0446\u0438\u0440\u0443\u0435\u043c\u0430, \u043a\u043e\u0433\u0434\u0430 \u043e\u043d\u0430 \u043e\u0442\u043b\u0438\u0447\u043d\u0430 \u043e\u0442 \u043d\u0443\u043b\u044f, \u0438 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u043b\u043e\u0433\u0430\u0440\u0438\u0444\u043c\u044b.  \u041a\u0440\u043e\u043c\u0435 \u0442\u043e\u0433\u043e, \u043c\u044b \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u044f\u0435\u043c \u0442\u0440\u0430\u0435\u043a\u0442\u043e\u0440\u0438\u044e \u0441\u043e\u0441\u0442\u043e\u044f\u043d\u0438\u044f-\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f (\u03c4) \u043a\u0430\u043a \u043f\u043e\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0441\u043e\u0441\u0442\u043e\u044f\u043d\u0438\u0439, \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0439 \u0438 \u043d\u0430\u0433\u0440\u0430\u0434: \u03c4 = (s0,a0,r0, s1,a1,r1\u2026, st,at,rt).<\/p>\n<div class=\"math\"><span class=\"katex-display\"><span class=\"katex\"><span class=\"katex-mathml\"><math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"block\"><semantics><mrow><mi>\u03b8<\/mi><mo>\u2190<\/mo><mi>\u03b8<\/mi><mo>+<\/mo><mi>\u03b1<\/mi><msub><mi mathvariant=\"normal\">\u2207<\/mi><mi>\u03b8<\/mi><\/msub><mi>\u0414\u0436<\/mi><mo stretchy=\"false\">(<\/mo><mi>\u03b8<\/mi><mo stretchy=\"false\">)<\/mo><mspace linebreak=\"newline\"\/><\/mrow><annotation encoding=\"application\/x-tex\">\\ \u0442\u0435\u0442\u0430 \\ \u0441\u0442\u0440\u0435\u043b\u0430 \u0432\u043b\u0435\u0432\u043e \\ \u0442\u0435\u0442\u0430 + \\ \u0430\u043b\u044c\u0444\u0430 \\ \u043d\u0430\u0431\u043b\u0430 _ {\\ \u0442\u0435\u0442\u0430} J (\\ \u0442\u0435\u0442\u0430) \\\\<\/annotation><\/semantics><\/math><\/span><span class=\"katex-html\" aria-hidden=\"true\"><span class=\"base\"><span class=\"strut\" style=\"height:0.69444em;vertical-align:0em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">\u03b8<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><span class=\"mrel\">\u2190<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><\/span><span class=\"base\"><span class=\"strut\" style=\"height:0.77777em;vertical-align:-0.08333em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">\u03b8<\/span><span class=\"mspace\" style=\"margin-right:0.2222222222222222em\"\/><span class=\"mbin\">+<\/span><span class=\"mspace\" style=\"margin-right:0.2222222222222222em\"\/><\/span><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.0037em\">\u03b1<\/span><span class=\"mord\"><span class=\"mord\">\u2207<\/span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.33610799999999996em\"><span style=\"top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em\"><span class=\"pstrut\" style=\"height:2.7em\"\/><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mathnormal mtight\" style=\"margin-right:0.02778em\">\u03b8<\/span><\/span><\/span><\/span><\/span><span class=\"vlist-s\">\u200b<\/span><\/span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em\"><span\/><\/span><\/span><\/span><\/span><\/span><span class=\"mord mathnormal\" style=\"margin-right:0.09618em\">\u0414\u0436<\/span><span class=\"mopen\">(<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">\u03b8<\/span><span class=\"mclose\">)<\/span><\/span><span class=\"mspace newline\"\/><\/span><\/span><\/span><\/div>\n<div class=\"math\"><span class=\"katex-display\"><span class=\"katex\"><span class=\"katex-mathml\"><math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"block\"><semantics><mrow><msub><mi mathvariant=\"normal\">\u2207<\/mi><mi>\u03b8<\/mi><\/msub><mi>\u0414\u0436<\/mi><mo stretchy=\"false\">(<\/mo><mi>\u03b8<\/mi><mo stretchy=\"false\">)<\/mo><mo>&#8220;=&#8221;<\/mo><msub><mi>\u0415<\/mi><mi>\u03c0<\/mi><\/msub><mrow><mo fence=\"true\">[<\/mo><msub><mi mathvariant=\"normal\">\u2207<\/mi><mi>\u03b8<\/mi><\/msub><mo stretchy=\"false\">(<\/mo><mi>log<\/mi><mo>\u2061<\/mo><mi>\u03c0<\/mi><mo stretchy=\"false\">(<\/mo><mi>\u03c4<\/mi><mi mathvariant=\"normal\">\u2223<\/mi><mi>\u03b8<\/mi><mo stretchy=\"false\">)<\/mo><mo stretchy=\"false\">)<\/mo><mi>R<\/mi><mo stretchy=\"false\">(<\/mo><mi>\u03c4<\/mi><mo stretchy=\"false\">)<\/mo><mo fence=\"true\">]<\/mo><\/mrow><\/mrow><annotation encoding=\"application\/x-tex\">\\nabla_{\\theta} J(\\theta)=E_{\\pi}\\left[\\nabla_{\\theta}(\\log \\pi(\\tau | \\theta)) R(\\tau)\\right]<\/annotation><\/semantics><\/math><\/span><span class=\"katex-html\" aria-hidden=\"true\"><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em\"\/><span class=\"mord\"><span class=\"mord\">\u2207<\/span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.33610799999999996em\"><span style=\"top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em\"><span class=\"pstrut\" style=\"height:2.7em\"\/><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mathnormal mtight\" style=\"margin-right:0.02778em\">\u03b8<\/span><\/span><\/span><\/span><\/span><span class=\"vlist-s\">\u200b<\/span><\/span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em\"><span\/><\/span><\/span><\/span><\/span><\/span><span class=\"mord mathnormal\" style=\"margin-right:0.09618em\">\u0414\u0436<\/span><span class=\"mopen\">(<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">\u03b8<\/span><span class=\"mclose\">)<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><span class=\"mrel\">&#8220;=&#8221;<\/span><span class=\"mspace\" style=\"margin-right:0.2777777777777778em\"\/><\/span><span class=\"base\"><span class=\"strut\" style=\"height:1em;vertical-align:-0.25em\"\/><span class=\"mord\"><span class=\"mord mathnormal\" style=\"margin-right:0.05764em\">\u0415<\/span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.151392em\"><span style=\"top:-2.5500000000000003em;margin-left:-0.05764em;margin-right:0.05em\"><span class=\"pstrut\" style=\"height:2.7em\"\/><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mathnormal mtight\" style=\"margin-right:0.03588em\">\u03c0<\/span><\/span><\/span><\/span><\/span><span class=\"vlist-s\">\u200b<\/span><\/span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em\"><span\/><\/span><\/span><\/span><\/span><\/span><span class=\"mspace\" style=\"margin-right:0.16666666666666666em\"\/><span class=\"minner\"><span class=\"mopen delimcenter\" style=\"top:0em\">[<\/span><span class=\"mord\"><span class=\"mord\">\u2207<\/span><span class=\"msupsub\"><span class=\"vlist-t vlist-t2\"><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.33610799999999996em\"><span style=\"top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em\"><span class=\"pstrut\" style=\"height:2.7em\"\/><span class=\"sizing reset-size6 size3 mtight\"><span class=\"mord mtight\"><span class=\"mord mathnormal mtight\" style=\"margin-right:0.02778em\">\u03b8<\/span><\/span><\/span><\/span><\/span><span class=\"vlist-s\">\u200b<\/span><\/span><span class=\"vlist-r\"><span class=\"vlist\" style=\"height:0.15em\"><span\/><\/span><\/span><\/span><\/span><\/span><span class=\"mopen\">(<\/span><span class=\"mop\">lo<span style=\"margin-right:0.01389em\">g<\/span><\/span><span class=\"mspace\" style=\"margin-right:0.16666666666666666em\"\/><span class=\"mord mathnormal\" style=\"margin-right:0.03588em\">\u03c0<\/span><span class=\"mopen\">(<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.1132em\">\u03c4<\/span><span class=\"mord\">\u2223<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.02778em\">\u03b8<\/span><span class=\"mclose\">)<\/span><span class=\"mclose\">)<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.00773em\">R<\/span><span class=\"mopen\">(<\/span><span class=\"mord mathnormal\" style=\"margin-right:0.1132em\">\u03c4<\/span><span class=\"mclose\">)<\/span><span class=\"mclose delimcenter\" style=\"top:0em\">]<\/span><\/span><\/span><\/span><\/span><\/span><\/div>\n<p>\u042f \u0434\u0443\u043c\u0430\u044e, \u0447\u0442\u043e \u0434\u043e\u0441\u0442\u0430\u0442\u043e\u0447\u043d\u043e \u043c\u0430\u0442\u0435\u043c\u0430\u0442\u0438\u043a\u0438 \u0434\u043b\u044f \u043e\u0434\u043d\u043e\u0433\u043e \u0434\u043d\u044f.  \u0412 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0435, \u043a\u043e\u043d\u0435\u0447\u043d\u043e \u0436\u0435, \u0443 \u043d\u0430\u0441 \u0435\u0441\u0442\u044c \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442 \u0432 \u0430\u043d\u0430\u043b\u0438\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0439 \u0444\u043e\u0440\u043c\u0435, \u0438 \u0442\u0435\u043f\u0435\u0440\u044c \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u043f\u0440\u0438\u043c\u0435\u043d\u0438\u0442\u044c \u043d\u0430\u0448 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c.<\/p>\n<p>\u0410\u043b\u0433\u043e\u0440\u0438\u0442\u043c, \u043e\u043f\u0438\u0441\u0430\u043d\u043d\u044b\u0439 \u0434\u043e \u0441\u0438\u0445 \u043f\u043e\u0440 (\u0441 \u043d\u0435\u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u0440\u0430\u0437\u043d\u0438\u0446\u0435\u0439), \u043d\u0430\u0437\u044b\u0432\u0430\u0435\u0442\u0441\u044f<br \/>\n<strong>\u0423\u041a\u0420\u0415\u041f\u0418\u0422\u042c<\/strong> \u0438\u043b\u0438 <strong>\u0413\u0440\u0430\u0434\u0438\u0435\u043d\u0442 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u041c\u043e\u043d\u0442\u0435-\u041a\u0430\u0440\u043b\u043e<\/strong>.  \u041e\u0442\u043b\u0438\u0447\u0438\u0435 \u043e\u0442 \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043e\u0432 \u0432\u0430\u043d\u0438\u043b\u044c\u043d\u043e\u0439 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e \u043c\u044b \u0438\u0437\u0431\u0430\u0432\u0438\u043b\u0438\u0441\u044c \u043e\u0442 \u043e\u0436\u0438\u0434\u0430\u043d\u0438\u044f \u0432 \u043d\u0430\u0433\u0440\u0430\u0434\u0435, \u0442\u0430\u043a \u043a\u0430\u043a \u044d\u0442\u043e \u043d\u0435 \u043e\u0447\u0435\u043d\u044c \u043f\u0440\u0430\u043a\u0442\u0438\u0447\u043d\u043e.  \u0412\u043c\u0435\u0441\u0442\u043e \u044d\u0442\u043e\u0433\u043e \u043c\u044b \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c \u0441\u0442\u043e\u0445\u0430\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u044b\u0439 \u0441\u043f\u0443\u0441\u043a \u0434\u043b\u044f \u043e\u0431\u043d\u043e\u0432\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u0442\u0430.  \u041c\u044b <strong>\u043e\u0431\u0440\u0430\u0437\u0435\u0446<\/strong> \u043e\u0442 \u043e\u0436\u0438\u0434\u0430\u043d\u0438\u044f \u0440\u0430\u0441\u0441\u0447\u0438\u0442\u0430\u0442\u044c \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0435 \u0437\u0430 \u044d\u043f\u0438\u0437\u043e\u0434 \u0438 \u0437\u0430\u0442\u0435\u043c \u043e\u0431\u043d\u043e\u0432\u0438\u0442\u044c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0434\u043b\u044f \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u0448\u0430\u0433\u0430 \u044d\u043f\u0438\u0437\u043e\u0434\u0430.  \u042d\u0442\u043e \u0434\u043e\u0432\u043e\u043b\u044c\u043d\u043e \u043f\u0440\u043e\u0441\u0442\u043e\u0439 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c.<\/p>\n<p>\u0425\u043e\u0440\u043e\u0448\u043e, \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0443\u043f\u0440\u043e\u0441\u0442\u0438\u043c \u0432\u0441\u0435 \u044d\u0442\u0438 \u0432\u0435\u0449\u0438.  \u0412\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0434\u0443\u043c\u0430\u0442\u044c \u043e \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u0430\u0445 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0442\u0430\u043a:<\/p>\n<p>\u0414\u043b\u044f \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u044d\u043f\u0438\u0437\u043e\u0434\u0430, \u0432 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u043c\u044b \u043f\u043e\u043b\u0443\u0447\u0438\u043b\u0438 \u043f\u043e\u043b\u043e\u0436\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0435 \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0435, \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c \u0431\u0443\u0434\u0435\u0442 \u0443\u0432\u0435\u043b\u0438\u0447\u0438\u0432\u0430\u0442\u044c \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e\u0441\u0442\u044c \u044d\u0442\u0438\u0445 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0439 \u0432 \u0431\u0443\u0434\u0443\u0449\u0435\u043c.  \u0422\u043e\u0447\u043d\u043e \u0442\u0430\u043a \u0436\u0435 \u0434\u043b\u044f \u043e\u0442\u0440\u0438\u0446\u0430\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0439 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u044b \u0443\u043c\u0435\u043d\u044c\u0448\u0430\u0442 \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e\u0441\u0442\u044c \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0439.  \u0412 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0435 \u0441\u043e \u0432\u0440\u0435\u043c\u0435\u043d\u0435\u043c \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f, \u043f\u0440\u0438\u0432\u043e\u0434\u044f\u0449\u0438\u0435 \u043a \u043e\u0442\u0440\u0438\u0446\u0430\u0442\u0435\u043b\u044c\u043d\u044b\u043c \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0430\u043c, \u0431\u0443\u0434\u0443\u0442 \u043f\u043e\u0441\u0442\u0435\u043f\u0435\u043d\u043d\u043e \u043e\u0442\u0444\u0438\u043b\u044c\u0442\u0440\u043e\u0432\u044b\u0432\u0430\u0442\u044c\u0441\u044f, \u0430 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f \u0441 \u043f\u043e\u043b\u043e\u0436\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u043c\u0438 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0430\u043c\u0438 \u0431\u0443\u0434\u0443\u0442 \u0441\u0442\u0430\u043d\u043e\u0432\u0438\u0442\u044c\u0441\u044f \u0432\u0441\u0435 \u0431\u043e\u043b\u0435\u0435 \u0438 \u0431\u043e\u043b\u0435\u0435 \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u044b\u043c\u0438.  \u0412\u043e\u0442 \u0438 \u0432\u0441\u0435.  \u0415\u0441\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435 \u0437\u0430\u043f\u043e\u043c\u043d\u0438\u0442\u044c \u0447\u0442\u043e-\u0442\u043e \u043e\u0434\u043d\u043e \u0438\u0437 \u0432\u0441\u0435\u0439 \u0441\u0442\u0430\u0442\u044c\u0438, \u0442\u043e \u044d\u0442\u043e \u043e\u043d\u043e.  \u0412 \u044d\u0442\u043e\u043c \u0441\u0443\u0442\u044c \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043e\u0432 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438.  \u0415\u0434\u0438\u043d\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0435, \u0447\u0442\u043e \u043a\u0430\u0436\u0434\u044b\u0439 \u0440\u0430\u0437 \u043c\u0435\u043d\u044f\u0435\u0442\u0441\u044f, \u044d\u0442\u043e \u0442\u043e, \u043a\u0430\u043a \u043c\u044b \u0432\u044b\u0447\u0438\u0441\u043b\u044f\u0435\u043c \u0432\u043e\u0437\u043d\u0430\u0433\u0440\u0430\u0436\u0434\u0435\u043d\u0438\u0435, \u043a\u0430\u043a\u0443\u044e \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0443 \u0432\u044b\u0431\u0438\u0440\u0430\u0435\u043c (Softmax, Gaussian \u0438 \u0442. \u0434.) \u0438 \u043a\u0430\u043a \u043c\u044b \u043e\u0431\u043d\u043e\u0432\u043b\u044f\u0435\u043c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b.<\/p>\n<p>\u0422\u0435\u043f\u0435\u0440\u044c \u0434\u0430\u0432\u0430\u0439\u0442\u0435 \u0434\u0432\u0438\u0433\u0430\u0442\u044c\u0441\u044f \u0434\u0430\u043b\u044c\u0448\u0435.<\/p>\n<div class=\"inline-newsletter-form\">\n<p><h2>\u0417\u0430\u0433\u0440\u0443\u0437\u0438\u0442\u0435 \u043d\u0430\u0448\u0443 \u0431\u0435\u0441\u043f\u043b\u0430\u0442\u043d\u0443\u044e \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u0443\u044e \u043a\u043d\u0438\u0433\u0443 \u043f\u043e \u0433\u043b\u0443\u0431\u043e\u043a\u043e\u043c\u0443 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044e \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c<\/h2>\n<h4>\u041c\u044b \u043e\u0431\u044a\u0435\u0434\u0438\u043d\u0438\u043b\u0438 \u0432\u0441\u0435 \u0441\u0442\u0430\u0442\u044c\u0438 \u043f\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044e \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c \u0432 \u043e\u0434\u0438\u043d PDF-\u0444\u0430\u0439\u043b.  \u041f\u043e\u044d\u0442\u043e\u043c\u0443, \u0435\u0441\u043b\u0438 \u0443 \u0432\u0430\u0441 \u043d\u0435\u0442 \u0432\u0440\u0435\u043c\u0435\u043d\u0438 \u0447\u0438\u0442\u0430\u0442\u044c \u0432\u0441\u044e \u0441\u0442\u0430\u0442\u044c\u044e \u0438\u043b\u0438 \u0432\u044b \u0445\u043e\u0442\u0438\u0442\u0435, \u0447\u0442\u043e\u0431\u044b pdf-\u0432\u0435\u0440\u0441\u0438\u044f \u0447\u0438\u0442\u0430\u043b\u0430\u0441\u044c \u0432 \u0430\u0432\u0442\u043e\u043d\u043e\u043c\u043d\u043e\u043c \u0440\u0435\u0436\u0438\u043c\u0435, \u043d\u0430\u0436\u043c\u0438\u0442\u0435 \u043a\u043d\u043e\u043f\u043a\u0443 \u043d\u0438\u0436\u0435.<\/h4>\n<\/p>\n<div id=\"mauticform_wrapper__drlebook\" class=\"mauticform-wrapper\">\n<div class=\"form-privacy-text--dark\">\n<p>* \u041c\u044b \u0441\u0442\u0440\u0435\u043c\u0438\u043c\u0441\u044f \u043a \u0432\u0430\u0448\u0435\u0439 \u043a\u043e\u043d\u0444\u0438\u0434\u0435\u043d\u0446\u0438\u0430\u043b\u044c\u043d\u043e\u0441\u0442\u0438.  AI Summer \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u043d\u0443\u044e \u0432\u0430\u043c\u0438 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044e \u0434\u043b\u044f \u043e\u0442\u043f\u0440\u0430\u0432\u043a\u0438 \u0432\u0430\u043c \u043d\u0430\u0448\u0435\u0433\u043e \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u043e\u043d\u043d\u043e\u0433\u043e \u0431\u044e\u043b\u043b\u0435\u0442\u0435\u043d\u044f \u0438 \u0441\u0432\u044f\u0437\u0438 \u0441 \u0432\u0430\u043c\u0438 \u043f\u043e \u043f\u043e\u0432\u043e\u0434\u0443 \u043d\u0430\u0448\u0438\u0445 \u043f\u0440\u043e\u0434\u0443\u043a\u0442\u043e\u0432.  \u0412\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u043e\u0442\u043a\u0430\u0437\u0430\u0442\u044c\u0441\u044f \u043e\u0442 \u043f\u043e\u0434\u043f\u0438\u0441\u043a\u0438 \u043d\u0430 \u044d\u0442\u0438 \u0441\u043e\u043e\u0431\u0449\u0435\u043d\u0438\u044f \u0432 \u043b\u044e\u0431\u043e\u0435 \u0432\u0440\u0435\u043c\u044f.  \u0414\u043b\u044f \u043f\u043e\u043b\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0439 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u0438 \u043e\u0437\u043d\u0430\u043a\u043e\u043c\u044c\u0442\u0435\u0441\u044c \u0441 \u043d\u0430\u0448\u0438\u043c<!-- --> \u041f\u043e\u043b\u0438\u0442\u0438\u043a\u0430 \u043a\u043e\u043d\u0444\u0438\u0434\u0435\u043d\u0446\u0438\u0430\u043b\u044c\u043d\u043e\u0441\u0442\u0438.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p>REINFORCE, \u043a\u0430\u043a \u0443\u0436\u0435 \u0443\u043f\u043e\u043c\u0438\u043d\u0430\u043b\u043e\u0441\u044c, \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u043e\u043c \u0441\u0442\u043e\u0445\u0430\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043d\u043e\u0433\u043e \u0441\u043f\u0443\u0441\u043a\u0430.  \u0423\u0447\u0438\u0442\u044b\u0432\u0430\u044f \u044d\u0442\u043e, \u0432\u043e\u0437\u043d\u0438\u043a\u0430\u0435\u0442 \u0432\u043e\u043f\u0440\u043e\u0441.  \u041f\u043e\u0447\u0435\u043c\u0443 \u0431\u044b \u043d\u0435 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438 \u0434\u043b\u044f \u0430\u043f\u043f\u0440\u043e\u043a\u0441\u0438\u043c\u0430\u0446\u0438\u0438 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0438 \u043e\u0431\u043d\u043e\u0432\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u0442\u0430?<\/p>\n<p>\u0411\u0438\u043d\u0433\u043e!!<\/p>\n<p>\u041f\u0440\u0438\u0448\u043b\u043e \u0432\u0440\u0435\u043c\u044f \u0432\u0432\u0435\u0441\u0442\u0438 \u0432 \u0443\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u0435 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438:<\/p>\n<p>\u041a\u043e\u043d\u0435\u0447\u043d\u043e, \u043c\u044b \u043c\u043e\u0436\u0435\u043c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u043f\u0440\u0430\u043a\u0442\u0438\u0447\u0435\u0441\u043a\u0438 \u043b\u044e\u0431\u0443\u044e \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0430\u043f\u043f\u0440\u043e\u043a\u0441\u0438\u043c\u0430\u0446\u0438\u0438 \u0444\u0443\u043d\u043a\u0446\u0438\u0438 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 (\u03c0), \u043d\u043e \u043c\u044b \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0443\u044e \u0441\u0435\u0442\u044c, \u0442\u0430\u043a\u0443\u044e \u200b\u200b\u043a\u0430\u043a \u0441\u0432\u0435\u0440\u0442\u043e\u0447\u043d\u0430\u044f \u0441\u0435\u0442\u044c, \u043f\u043e\u0442\u043e\u043c\u0443 \u0447\u0442\u043e \u043d\u0430\u043c \u043d\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0433\u043b\u0443\u0431\u043e\u043a\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435.  \u0418\u0437\u0432\u0435\u0441\u0442\u043d\u044b\u043c \u043f\u0440\u0438\u043c\u0435\u0440\u043e\u043c \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0430\u0433\u0435\u043d\u0442, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0443\u0447\u0438\u0442\u0441\u044f \u0438\u0433\u0440\u0430\u0442\u044c \u0432 \u0438\u0433\u0440\u0443 Pong, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u044b \u043f\u043e\u043b\u0438\u0442\u0438\u043a \u0438 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0435\u0442\u0438.  \u0412 \u044d\u0442\u043e\u043c \u043f\u0440\u0438\u043c\u0435\u0440\u0435 \u0441\u0435\u0442\u044c \u043f\u043e\u043b\u0443\u0447\u0430\u0435\u0442 \u0432 \u043a\u0430\u0447\u0435\u0441\u0442\u0432\u0435 \u0432\u0445\u043e\u0434\u043d\u044b\u0445 \u0434\u0430\u043d\u043d\u044b\u0445 \u043a\u0430\u0434\u0440\u044b \u0438\u0437 \u0438\u0433\u0440\u044b \u0438 \u0432\u044b\u0432\u043e\u0434\u0438\u0442 \u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e\u0441\u0442\u044c \u043f\u043e\u0432\u044b\u0448\u0435\u043d\u0438\u044f \u0438\u043b\u0438 \u043f\u043e\u043d\u0438\u0436\u0435\u043d\u0438\u044f.<\/p>\n<p><span class=\"gatsby-resp-image-wrapper\" style=\"position:relative;display:block;margin-left:auto;margin-right:auto;max-width:775px\"><\/p>\n<p>    <span class=\"gatsby-resp-image-background-image\" style=\"padding-bottom:43.333333333333336%;position:relative;bottom:0;left:0;background-image:url('data:image\/jpeg;base64,\/9j\/2wBDABALDA4MChAODQ4SERATGCgaGBYWGDEjJR0oOjM9PDkzODdASFxOQERXRTc4UG1RV19iZ2hnPk1xeXBkeFxlZ2P\/2wBDARESEhgVGC8aGi9jQjhCY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2NjY2P\/wgARCAAJABQDASIAAhEBAxEB\/8QAGAAAAwEBAAAAAAAAAAAAAAAAAAMEAQX\/xAAUAQEAAAAAAAAAAAAAAAAAAAAB\/9oADAMBAAIQAxAAAAGjpM0Yxwn\/xAAYEAADAQEAAAAAAAAAAAAAAAABAgMRIP\/aAAgBAQABBQKdnLjcSjHj\/8QAFREBAQAAAAAAAAAAAAAAAAAAARD\/2gAIAQMBAT8BWf\/EABURAQEAAAAAAAAAAAAAAAAAAAEQ\/9oACAECAQE\/ASf\/xAAYEAEAAwEAAAAAAAAAAAAAAAABECAjMf\/aAAgBAQAGPwIhze0\/\/8QAGRABAQEAAwAAAAAAAAAAAAAAAREAEDGh\/9oACAEBAAE\/IQyrdYe4Cikd44N\/\/9oADAMBAAIAAwAAABDDz\/\/EABYRAQEBAAAAAAAAAAAAAAAAAAEAEf\/aAAgBAwEBPxAF0Lb\/xAAWEQEBAQAAAAAAAAAAAAAAAAABEBH\/2gAIAQIBAT8QCGLP\/8QAGhAAAgMBAQAAAAAAAAAAAAAAAAERITFBcf\/aAAgBAQABPxBgIhyn2h497p2XNssraXTSFh16f\/\/Z');background-size:cover;display:block\"\/><br \/>\n  <img decoding=\"async\" class=\"gatsby-resp-image-image\" alt=\"pong_pg\" title=\"pong_pg\" src=\"https:\/\/theaisummer.com\/static\/65486dc93d9fe8cc73576a4cbace4033\/3fd11\/pong_pg.jpg\" srcset=\"\/static\/65486dc93d9fe8cc73576a4cbace4033\/f93b5\/pong_pg.jpg 300w,\/static\/65486dc93d9fe8cc73576a4cbace4033\/b4294\/pong_pg.jpg 600w,\/static\/65486dc93d9fe8cc73576a4cbace4033\/3fd11\/pong_pg.jpg 775w\" sizes=\"(max-width: 775px) 100vw, 775px\" style=\"width:100%;height:100%;margin:0;vertical-align:middle;position:absolute;top:0;left:0\" loading=\"lazy\"\/><\/p>\n<p>    <\/span><br \/>\n<em>http:\/\/karpathy.github.io\/2016\/05\/31\/rl\/<\/em><\/p>\n<p>\u041c\u044b \u043f\u043e\u043f\u0440\u043e\u0431\u0443\u0435\u043c \u0441\u0434\u0435\u043b\u0430\u0442\u044c \u0447\u0442\u043e-\u0442\u043e \u043f\u043e\u0434\u043e\u0431\u043d\u043e\u0435, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f \u0441\u0440\u0435\u0434\u0443 \u0442\u0440\u0435\u043d\u0430\u0436\u0435\u0440\u043d\u043e\u0433\u043e \u0437\u0430\u043b\u0430 \u043e\u0442 OpenAI.<\/p>\n<pre class=\"prism-code language-python\" style=\"color:#F8F8F2;background-color:#282A36\"><p><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">class<\/span><span class=\"token plain\"> <\/span><span class=\"token class-name\">REINFORCEAgent<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">def<\/span><span class=\"token plain\"> <\/span><span class=\"token function\" style=\"color:rgb(80, 250, 123)\">build_model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        model <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> Sequential<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">add<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">Dense<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">hidden1<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> input_dim<\/span><span class=\"token operator\">=<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">state_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> activation<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'relu'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> kernel_initializer<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'glorot_uniform'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">add<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">Dense<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">hidden2<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> activation<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'relu'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> kernel_initializer<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'glorot_uniform'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">add<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">Dense<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">action_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> activation<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'softmax'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> kernel_initializer<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'glorot_uniform'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">compile<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">loss<\/span><span class=\"token operator\">=<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">\"categorical_crossentropy\"<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> optimizer<\/span><span class=\"token operator\">=<\/span><span class=\"token plain\">Adam<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">lr<\/span><span class=\"token operator\">=<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">learning_rate<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">return<\/span><span class=\"token plain\"> model<\/span><\/p><p><span class=\"token plain\">    <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">def<\/span><span class=\"token plain\"> <\/span><span class=\"token function\" style=\"color:rgb(80, 250, 123)\">get_action<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        policy <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">predict<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> batch_size<\/span><span class=\"token operator\">=<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">flatten<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">return<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">random<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">choice<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">action_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> <\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> p<\/span><span class=\"token operator\">=<\/span><span class=\"token plain\">policy<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">def<\/span><span class=\"token plain\"> <\/span><span class=\"token function\" style=\"color:rgb(80, 250, 123)\">discount_rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        discounted_rewards <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">zeros_like<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        running_add <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> <\/span><span class=\"token number\">0<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">for<\/span><span class=\"token plain\"> t <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">in<\/span><span class=\"token plain\"> <\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">reversed<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">range<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> <\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">len<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            running_add <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> running_add <\/span><span class=\"token operator\">*<\/span><span class=\"token plain\"> self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">discount_factor <\/span><span class=\"token operator\">+<\/span><span class=\"token plain\"> rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">t<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            discounted_rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">t<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"> <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> running_add<\/span><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">return<\/span><span class=\"token plain\"> discounted_rewards<\/span><\/p><p><span class=\"token plain\">    <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">def<\/span><span class=\"token plain\"> <\/span><span class=\"token function\" style=\"color:rgb(80, 250, 123)\">train_model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        episode_length <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> <\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">len<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">states<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        discounted_rewards <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">discount_rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        discounted_rewards <\/span><span class=\"token operator\">-=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">mean<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">discounted_rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        discounted_rewards <\/span><span class=\"token operator\">\/=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">std<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">discounted_rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        update_inputs <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">zeros<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">episode_length<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">state_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        advantages <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">zeros<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">episode_length<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">action_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">for<\/span><span class=\"token plain\"> i <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">in<\/span><span class=\"token plain\"> <\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">range<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">episode_length<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            update_inputs<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">i<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"> <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">states<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">i<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            advantages<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">i<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">actions<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">i<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"> <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> discounted_rewards<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token plain\">i<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        self<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">fit<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">update_inputs<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> advantages<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> epochs<\/span><span class=\"token operator\">=<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> verbose<\/span><span class=\"token operator\">=<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">env <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> gym<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">make<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token string\" style=\"color:rgb(255, 121, 198)\">'CartPole-v1'<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">state_size <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> env<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">observation_space<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">shape<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">action_size <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> env<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">action_space<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">n<\/span><\/p><p><span class=\"token plain\">scores<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> episodes <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> <\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> <\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">agent <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> REINFORCEAgent<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">state_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> action_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\"\/><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">for<\/span><span class=\"token plain\"> e <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">in<\/span><span class=\"token plain\"> <\/span><span class=\"token builtin\" style=\"color:rgb(189, 147, 249)\">range<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">EPISODES<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    done <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> <\/span><span class=\"token boolean\">False<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    score <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> <\/span><span class=\"token number\">0<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    state <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> env<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">reset<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    state <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">reshape<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> <\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> state_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">    <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">while<\/span><span class=\"token plain\"> <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">not<\/span><span class=\"token plain\"> done<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">if<\/span><span class=\"token plain\"> agent<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">render<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            env<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">render<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        action <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> agent<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">get_action<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        next_state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> reward<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> done<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> info <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> env<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">step<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">action<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        next_state <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> np<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">reshape<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">next_state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> <\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> state_size<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">]<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        reward <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> reward <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">if<\/span><span class=\"token plain\"> <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">not<\/span><span class=\"token plain\"> done <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">or<\/span><span class=\"token plain\"> score <\/span><span class=\"token operator\">==<\/span><span class=\"token plain\"> <\/span><span class=\"token number\">499<\/span><span class=\"token plain\"> <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">else<\/span><span class=\"token plain\"> <\/span><span class=\"token operator\">-<\/span><span class=\"token number\">100<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        agent<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">append_sample<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">state<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> action<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">,<\/span><span class=\"token plain\"> reward<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">        score <\/span><span class=\"token operator\">+=<\/span><span class=\"token plain\"> reward<\/span><\/p><p><span class=\"token plain\">        state <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> next_state<\/span><\/p><p><span class=\"token plain\">        <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">if<\/span><span class=\"token plain\"> done<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">:<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            agent<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">train_model<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            score <\/span><span class=\"token operator\">=<\/span><span class=\"token plain\"> score <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">if<\/span><span class=\"token plain\"> score <\/span><span class=\"token operator\">==<\/span><span class=\"token plain\"> <\/span><span class=\"token number\">500<\/span><span class=\"token plain\"> <\/span><span class=\"token keyword\" style=\"color:rgb(189, 147, 249);font-style:italic\">else<\/span><span class=\"token plain\"> score <\/span><span class=\"token operator\">+<\/span><span class=\"token plain\"> <\/span><span class=\"token number\">100<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            scores<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">append<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">score<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><span class=\"token plain\"\/><\/p><p><span class=\"token plain\">            episodes<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">.<\/span><span class=\"token plain\">append<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">(<\/span><span class=\"token plain\">e<\/span><span class=\"token punctuation\" style=\"color:rgb(248, 248, 242)\">)<\/span><\/p><\/pre>\n<p>\u0412\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0432\u0438\u0434\u0435\u0442\u044c, \u0447\u0442\u043e \u044d\u0442\u043e \u043d\u0435 \u0442\u0440\u0438\u0432\u0438\u0430\u043b\u044c\u043d\u043e.  \u041c\u044b \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u044f\u0435\u043c \u043c\u043e\u0434\u0435\u043b\u044c \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u0438, \u0432\u044b\u0431\u043e\u0440\u043a\u0443 \u041c\u043e\u043d\u0442\u0435-\u041a\u0430\u0440\u043b\u043e, \u043f\u0440\u043e\u0446\u0435\u0441\u0441 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u0430 \u0437\u0430\u0442\u0435\u043c \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u043c \u0430\u0433\u0435\u043d\u0442\u0443 \u0443\u0447\u0438\u0442\u044c\u0441\u044f, \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0443\u044f \u0441 \u043e\u043a\u0440\u0443\u0436\u0430\u044e\u0449\u0435\u0439 \u0441\u0440\u0435\u0434\u043e\u0439, \u0438 \u043e\u0431\u043d\u043e\u0432\u043b\u044f\u0435\u043c \u0432\u0435\u0441 \u0432 \u043a\u043e\u043d\u0446\u0435 \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u044d\u043f\u0438\u0437\u043e\u0434\u0430.<\/p>\n<p>\u0414\u043b\u044f \u043f\u043e\u043b\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u043c\u0430\u0442\u0435\u0440\u0438\u0430\u043b\u043e\u0432 \u043e \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u0430\u0445 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u044f \u043d\u0430\u0441\u0442\u043e\u044f\u0442\u0435\u043b\u044c\u043d\u043e \u0440\u0435\u043a\u043e\u043c\u0435\u043d\u0434\u0443\u044e \u043a\u0443\u0440\u0441 Advanced AI: Deep Reinforcement Learning Course in Python \u043d\u0430 Udemy.  \u041e\u043d \u043e\u0445\u0432\u0430\u0442\u044b\u0432\u0430\u0435\u0442 \u0432\u0441\u0435, \u0447\u0442\u043e \u0432\u0430\u043c \u043d\u0443\u0436\u043d\u043e \u0437\u043d\u0430\u0442\u044c, \u043e\u0442 Deep Q Learning \u0434\u043e \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u043e\u0432 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0438 \u043a\u0440\u0438\u0442\u0438\u043a\u0438 \u0430\u043a\u0442\u0435\u0440\u043e\u0432.<\/p>\n<p>\u041d\u043e \u0433\u0440\u0430\u0434\u0438\u0435\u043d\u0442\u044b \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0438 \u0438\u043c\u0435\u044e\u0442 \u0441\u0432\u043e\u0438 \u043d\u0435\u0434\u043e\u0441\u0442\u0430\u0442\u043a\u0438.  \u041d\u0430\u0438\u0431\u043e\u043b\u0435\u0435 \u0432\u0430\u0436\u043d\u044b\u043c \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0442\u043e, \u0447\u0442\u043e \u043e\u043d\u0438 \u0438\u043c\u0435\u044e\u0442 \u0432\u044b\u0441\u043e\u043a\u0443\u044e \u0434\u0438\u0441\u043f\u0435\u0440\u0441\u0438\u044e, \u0438 \u0441\u0442\u0430\u0431\u0438\u043b\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u043c\u043e\u0434\u0435\u043b\u0438 \u043c\u043e\u0436\u0435\u0442 \u0431\u044b\u0442\u044c \u043e\u0447\u0435\u043d\u044c \u0441\u043b\u043e\u0436\u043d\u043e.<\/p>\n<p>\u0425\u043e\u0447\u0435\u0448\u044c \u0437\u043d\u0430\u0442\u044c, \u043a\u0430\u043a \u043c\u044b \u044d\u0442\u043e \u0440\u0435\u0448\u0438\u043c?  \u041f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0442\u044c \u0441\u0432\u044f\u0437\u044c&#8230;<\/p>\n<p>(\u041f\u043e\u0434\u0441\u043a\u0430\u0437\u043a\u0430: \u0435\u0433\u043e \u043c\u043e\u0434\u0435\u043b\u0438 \u0430\u043a\u0442\u0435\u0440\u043e\u0432-\u043a\u0440\u0438\u0442\u0438\u043a\u043e\u0432)<\/p>\n<div class=\"dl-prod-book-inline-banner\">\n<div class=\"dl-prod-book-inline-banner__image gatsby-image-wrapper\" style=\"position:relative;overflow:hidden\"><img decoding=\"async\" aria-hidden=\"true\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAABQAAAAZCAYAAAAxFw7TAAAACXBIWXMAAAsTAAALEwEAmpwYAAAFzklEQVQ4y1WU2VOb1xnGzyfVbt1O6tST4AVjglc2s1sskgxC8GlBIAmQkMRugtlBbAJjwAKMDYbYYOyMSTJt46YzSV1PO2k7uWimnfauF532or3oTC\/7L3R6+ev7SaGeXjxzzrf9znOe9\/2OUtm1qAs3UVl2tOybmLJlvGBDy7Kina9JyZRSNWaRKVPGzCq0c5WYDJ21oE6Xp5VRhlI5TtR79WmdrkG9UykPqmQuOlONelc+OCUvn5KX3y5B\/UD0drG8Z9wrRZ0sFri8a4DPiNRlF2aRAQyPrxNff87U2gFtw6tU+keIjCWJTawzvvKY2Y0Dhha2GVnaQY\/FCQ3d5dbsfTFQgSlLzIh7pa75UBdFWW5qe1fpTuzROb\/PVX2Y0uA0ocltAiMbtE9sEZ3ZJTi6SfPQBs7uRapDs\/iH1sStwM7ZUedtAsz1425uIhDw4vU6OVdSj8ftoMxWj8\/bwPVqB5lFdgotdhx1VtwNVoJuK9fK7ehOGzeqqrHW1lNgcXDich1KK2zn4wUPP7zj4XfbLg4THkZ7mni55ObpjJsv111M9Xn40xOdtqAH3ethc9TFyzs6S+\/r7Md1\/rDVwMsFJyfzpB7HSjqo8wXJqGynJ9aC2+9nsLuZtrbmFLjR18xkvwe\/30NvxEul04tN99Ag4NsxF5FWF\/W6Tle7zndzddlySSeqMIa6HkXlRVD5HaIwKleUJ7oYxJwXSs8vNcv9AOpKi8xFl+X6klGDJimqV649AizrRSvrQZV2YyrtRCuJoRVHMZfIAvltnKrpZ2f2EYVTEr61H5PAtII2TPmtaHkBNKmBltuCKVfgRoFVxQCq\/JaoH1XWh7GAAVeFEU44pjmdPGQucR9HZBLL4h6ZvoS4bJXn4rgglFpU5QXTzgWuVOUQyjKIuvE+R3BzWT9V\/juci39IxsAqnzbO0FQywFnnAGUrh1wJJMWlRHO94w24oD0NVzVjqOpRVNUIpqrhFNTqWmR5ag9\/KMFaU4KvJp9i8cxhzumg0NZLT\/QhVyvku6IIWpFEcz3yBq7scZRtSvKZQKsZF\/AYbk+cj1pn+bN+l78PPqY3usj3yjo4W9xLpkDHJp7SPvYzcSTAUsm\/uEskxS2S4qraedTNWdEMJvu0wOP01Y\/yr+ga\/+zZpcEhkRRIPvkBsotDXL0Wxj\/5gqEP\/yKuelI7Mkv+ZqO4BlzV30E5FlB1CUx1afi9lkW+GNgkw3FbYEGOF4c5WRqmqCjM3PkAv50\/YPfVP8gqHybTcpu3JH\/zUWGVvopqWEY575KCO5fIk9yOX5B\/M8fD8Ypuvl8RJV968UVBN\/+Ww4CvP+WvyedU3JjkRPUI\/1dY5d1AuaXHXPdIwRu\/gVtkVeOczGkkp7yTr9sm4bND+M0hf5u7z4B1ireMzK2i6rFUUZVRVNX8AOXbRDUJ2LMucGkJgWvG3LnIaWlW50U3fzx4xn9+\/3O+jK4SqZrnlMSkORJoRv5G9rKAqpkQoH8L1fKQFPgI3iJjYBtTaI9vh5+SaRujtGaQYNMyDlkkuy2JCm+jWh+ljegr\/K8WKZgBaN5MSZO56UjGvcADLi39iNatz7jSucV3\/Gt8yye78Bm7WMakG7nPCUxc1o4bW06DlO9+esuNRpbiQJexRa7DmxzresC127uUDz\/h3S5x1pRMO7LLb2g1YIvfdIp0iQHSDJhrjY6t1+grP6XjyS9p2X2NY\/MLYge\/5uba57Q+ek388Cv6nv0Kz84rIvu\/IPrgc2pnDjmmL6XaLr1lo8qpSic5G9sls2+P4AeviG3\/BHviCRVy7NfM7BBc2Wf00QtCy7s4kp9gufdj3uvbJVt+Q5PkmgYmDKC0jCeZVuNKKuCs4cf0LD\/j4foMQ4tTDC8MMZ24JadOHwtLg1intzgzsifZiSPb7BtYastHMKNdjFECvzoubjY+YmL1OcH5PYpHdsjo2uKdzodcuLVNSXyf7DEBSlG0+oU3sLo5\/gubMZbW7M93hgAAAABJRU5ErkJggg==\" alt=\"\u041a\u043d\u0438\u0433\u0430 \u00ab\u0413\u043b\u0443\u0431\u043e\u043a\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0432 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0441\u0442\u0432\u0435\u00bb\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;object-fit:contain;object-position:center;opacity:1;transition-delay:500ms\"\/><noscript><picture><source srcset=\"https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/69585\/deep-learning-book-cover.png 200w,&#10;https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/497c6\/deep-learning-book-cover.png 400w,&#10;https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/3c17d\/deep-learning-book-cover.png 720w\" sizes=\"(max-width: 720px) 100vw, 720px\"\/><img decoding=\"async\" loading=\"lazy\" sizes=\"(max-width: 720px) 100vw, 720px\" srcset=\"https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/69585\/deep-learning-book-cover.png 200w,&#10;https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/497c6\/deep-learning-book-cover.png 400w,&#10;https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/3c17d\/deep-learning-book-cover.png 720w\" src=\"https:\/\/theaisummer.com\/static\/502e7c498dd9d981ac44c1dcd10f9276\/3c17d\/deep-learning-book-cover.png\" alt=\"\u041a\u043d\u0438\u0433\u0430 \u00ab\u0413\u043b\u0443\u0431\u043e\u043a\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0432 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0441\u0442\u0432\u0435\u00bb\" style=\"position:absolute;top:0;left:0;opacity:1;width:100%;height:100%;object-fit:cover;object-position:center\"\/><\/picture><\/noscript><\/div>\n<div class=\"dl-prod-book-inline-banner__text\">\n<h2>\u041a\u043d\u0438\u0433\u0430 \u00ab\u0413\u043b\u0443\u0431\u043e\u043a\u043e\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0432 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0441\u0442\u0432\u0435\u00bb \ud83d\udcd6<\/h2>\n<h4>\u0423\u0437\u043d\u0430\u0439\u0442\u0435, \u043a\u0430\u043a \u0441\u043e\u0437\u0434\u0430\u0432\u0430\u0442\u044c, \u043e\u0431\u0443\u0447\u0430\u0442\u044c, \u0440\u0430\u0437\u0432\u0435\u0440\u0442\u044b\u0432\u0430\u0442\u044c, \u043c\u0430\u0441\u0448\u0442\u0430\u0431\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0438 \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0442\u044c \u043c\u043e\u0434\u0435\u043b\u0438 \u0433\u043b\u0443\u0431\u043e\u043a\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f.  \u0418\u0437\u0443\u0447\u0438\u0442\u0435 \u0438\u043d\u0444\u0440\u0430\u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0443 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0438 MLOps \u043d\u0430 \u043f\u0440\u0430\u043a\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u043f\u0440\u0438\u043c\u0435\u0440\u0430\u0445.<\/h4>\n<p>\u0423\u0437\u043d\u0430\u0442\u044c \u0431\u043e\u043b\u044c\u0448\u0435<\/p><\/div>\n<\/div>\n<p><em class=\"affiliate-disclosure\">* \u0420\u0430\u0441\u043a\u0440\u044b\u0442\u0438\u0435 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u0438: \u041e\u0431\u0440\u0430\u0442\u0438\u0442\u0435 \u0432\u043d\u0438\u043c\u0430\u043d\u0438\u0435, \u0447\u0442\u043e \u043d\u0435\u043a\u043e\u0442\u043e\u0440\u044b\u0435 \u0438\u0437 \u043f\u0440\u0438\u0432\u0435\u0434\u0435\u043d\u043d\u044b\u0445 \u0432\u044b\u0448\u0435 \u0441\u0441\u044b\u043b\u043e\u043a \u043c\u043e\u0433\u0443\u0442 \u0431\u044b\u0442\u044c \u043f\u0430\u0440\u0442\u043d\u0435\u0440\u0441\u043a\u0438\u043c\u0438 \u0441\u0441\u044b\u043b\u043a\u0430\u043c\u0438, \u0438 \u043c\u044b \u0431\u0435\u0437 \u0434\u043e\u043f\u043e\u043b\u043d\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0445 \u0437\u0430\u0442\u0440\u0430\u0442 \u0434\u043b\u044f \u0432\u0430\u0441 \u043f\u043e\u043b\u0443\u0447\u0438\u043c \u043a\u043e\u043c\u0438\u0441\u0441\u0438\u044e, \u0435\u0441\u043b\u0438 \u0432\u044b \u0440\u0435\u0448\u0438\u0442\u0435 \u0441\u043e\u0432\u0435\u0440\u0448\u0438\u0442\u044c \u043f\u043e\u043a\u0443\u043f\u043a\u0443 \u043f\u043e\u0441\u043b\u0435 \u043f\u0435\u0440\u0435\u0445\u043e\u0434\u0430 \u043f\u043e \u0441\u0441\u044b\u043b\u043a\u0435.<\/em><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u041d\u0430 \u044d\u0442\u043e\u0442 \u0440\u0430\u0437 \u043c\u044b \u0441\u043e\u0431\u0438\u0440\u0430\u0435\u043c\u0441\u044f \u0437\u0430\u043d\u044f\u0442\u044c \u0441\u0435\u0431\u044f \u0434\u0440\u0443\u0433\u0438\u043c \u0441\u0435\u043c\u0435\u0439\u0441\u0442\u0432\u043e\u043c \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u043e\u0432 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c, \u043d\u0430\u0437\u044b\u0432\u0430\u0435\u043c\u044b\u0445 \u043c\u0435\u0442\u043e\u0434\u0430\u043c\u0438, \u043e\u0441\u043d\u043e\u0432\u0430\u043d\u043d\u044b\u043c\u0438 \u043d\u0430 \u043f\u043e\u043b\u0438\u0442\u0438\u043a\u0435. \u0415\u0441\u043b\u0438 \u0432\u044b \u043f\u043e\u043c\u043d\u0438\u0442\u0435, \u0435\u0441\u0442\u044c \u0434\u0432\u0435 \u043e\u0441\u043d\u043e\u0432\u043d\u044b\u0435 \u0433\u0440\u0443\u043f\u043f\u044b \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0441 \u043f\u043e\u0434\u043a\u0440\u0435\u043f\u043b\u0435\u043d\u0438\u0435\u043c \u0431\u0435\u0437 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439. \u041c\u044b \u0430\u043d\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u043f\u0435\u0440\u0432\u044b\u0435 \u0432 \u0434\u0432\u0443\u0445 \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0438\u0445 \u0441\u0442\u0430\u0442\u044c\u044f\u0445, \u0433\u0434\u0435 \u043c\u044b \u0433\u043e\u0432\u043e\u0440\u0438\u043b\u0438 \u043e Q-learning \u0438 Deep Q Networks, \u0430 \u0442\u0430\u043a\u0436\u0435 \u043e \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0445 \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f\u0445 \u0431\u0430\u0437\u043e\u0432\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439, [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":1569,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":{"0":"post-1568","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-ai-research-and-news"},"_links":{"self":[{"href":"https:\/\/gptmain.news\/index.php?rest_route=\/wp\/v2\/posts\/1568","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gptmain.news\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gptmain.news\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gptmain.news\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/gptmain.news\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1568"}],"version-history":[{"count":0,"href":"https:\/\/gptmain.news\/index.php?rest_route=\/wp\/v2\/posts\/1568\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gptmain.news\/index.php?rest_route=\/wp\/v2\/media\/1569"}],"wp:attachment":[{"href":"https:\/\/gptmain.news\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1568"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gptmain.news\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1568"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gptmain.news\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1568"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}