{"id":36896,"date":"2025-01-20T19:00:24","date_gmt":"2025-01-20T11:00:24","guid":{"rendered":"https:\/\/17aitech.com\/?p=36896"},"modified":"2025-01-20T19:00:24","modified_gmt":"2025-01-20T11:00:24","slug":"%e6%b5%81%e5%bc%8f%e6%b7%b1%e5%ba%a6%e5%ad%a6%e4%b9%a0%e7%bb%88%e4%ba%8e%e5%a5%8f%e6%95%88%e4%ba%86%ef%bc%81%e5%bc%ba%e5%8c%96%e5%ad%a6%e4%b9%a0%e4%b9%8b%e7%88%b6richard-sutton%e5%8a%9b%e8%8d%90","status":"publish","type":"post","link":"https:\/\/17aitech.com\/?p=36896","title":{"rendered":"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350"},"content":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2024-11-29-7\" target=\"_blank\">\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350<\/a><\/p>\n<section>\u81ea\u7136\u667a\u80fd\uff08Natural intelligence\uff09\u8fc7\u7a0b\u5c31\u50cf\u4e00\u6761\u8fde\u7eed\u7684\u6d41\uff0c\u53ef\u4ee5\u5b9e\u65f6\u5730\u611f\u77e5\u3001\u884c\u52a8\u548c\u5b66\u4e60\u3002\u6d41\u5f0f\u5b66\u4e60\u662f Q \u5b66\u4e60\u548c TD \u7b49\u7ecf\u5178\u5f3a\u5316\u5b66\u4e60 (RL) \u7b97\u6cd5\u7684\u8fd0\u4f5c\u65b9\u5f0f\uff0c\u5b83\u901a\u8fc7\u4f7f\u7528\u6700\u65b0\u6837\u672c\u800c\u4e0d\u5b58\u50a8\u6837\u672c\u6765\u6a21\u4eff\u81ea\u7136\u5b66\u4e60\u3002\u8fd9\u79cd\u65b9\u6cd5\u4e5f\u975e\u5e38\u9002\u5408\u8d44\u6e90\u53d7\u9650\u3001\u901a\u4fe1\u53d7\u9650\u548c\u9690\u79c1\u654f\u611f\u7684\u5e94\u7528\u7a0b\u5e8f\u3002<\/section>\n<section><\/section>\n<section>\u7136\u800c\uff0c\u5728\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u4e2d\uff0c\u5b66\u4e60\u5668\uff08learners \uff09\u51e0\u4e4e\u603b\u662f\u4f7f\u7528\u6279\u91cf\u66f4\u65b0\u548c\u91cd\u653e\u7f13\u51b2\u533a\uff0c\u8fd9\u79cd\u65b9\u5f0f\u4f7f\u5f97\u5b83\u4eec\u5728\u8ba1\u7b97\u4e0a\u5f88\u6602\u8d35\uff0c\u5e76\u4e14\u4e0e\u6d41\u5f0f\u5b66\u4e60\u4e0d\u517c\u5bb9\u3002<\/section>\n<section><\/section>\n<section>\u7814\u7a76\u8ba4\u4e3a\u6279\u91cf\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u4e4b\u6240\u4ee5\u666e\u904d\uff0c\u662f\u56e0\u4e3a\u5b83\u7684\u6837\u672c\u6548\u7387\u9ad8\u3002\u6d41\u5f0f\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u5b58\u5728\u6837\u672c\u6548\u7387\u95ee\u9898\uff0c\u7ecf\u5e38\u51fa\u73b0\u4e0d\u7a33\u5b9a\u548c\u5b66\u4e60\u5931\u8d25\u7684\u60c5\u51b5\u3002\u8fd9\u4e00\u73b0\u8c61\u79f0\u4e3a\u6d41\u5f0f\u969c\u788d\u3002<\/section>\n<section><\/section>\n<section>\u5c31\u50cf\u4e0b\u56fe\u5c55\u793a\u7684\uff0c\u6d41\u5f0f\u5f3a\u5316\u5b66\u4e60\u9700\u8981\u4ece\u5373\u65f6\u5355\u4e2a\u6837\u672c\u8fdb\u884c\u66f4\u65b0\uff0c\u800c\u65e0\u9700\u5b58\u50a8\u8fc7\u53bb\u7684\u6837\u672c\uff0c\u800c\u6279\u91cf\u5f3a\u5316\u5b66\u4e60\u5219\u4f9d\u8d56\u4e8e\u5b58\u50a8\u5728\u91cd\u653e\u7f13\u51b2\u533a\u4e2d\u7684\u8fc7\u53bb\u6837\u672c\u7684\u6279\u91cf\u66f4\u65b0\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-f5c534d6ffe06dacee7027c874265724.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-f5c534d6ffe06dacee7027c874265724.png\"><\/a><\/section>\n<section>\u4e3a\u4e86\u89e3\u51b3\u6d41\u5f0f\u969c\u788d\uff0c\u672c\u6587\u6765\u81ea\u963f\u5c14\u4f2f\u5854\u5927\u5b66\u7b49\u673a\u6784\u7684\u7814\u7a76\u8005\u63d0\u51fa\u4e86 stream-x \u7b97\u6cd5\uff0c\u8fd9\u662f\u7b2c\u4e00\u7c7b\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u7b97\u6cd5\uff0c\u7528\u4e8e\u514b\u670d\u9884\u6d4b\u548c\u63a7\u5236\u6d41\u5f0f\u969c\u788d\uff0c\u5e76\u5339\u914d\u6279\u91cf\u5f3a\u5316\u5b66\u4e60\u7684\u6837\u672c\u6548\u7387\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-230f54eb2266b2d853726bdd0bdee23d.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-230f54eb2266b2d853726bdd0bdee23d.png\"><\/a><\/section>\n<ul>\n<li>\n<section>\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/openreview.net\/pdf?id=yqQJGTDGXN<\/section>\n<\/li>\n<li>\n<section>\u9879\u76ee\u5730\u5740\uff1ahttps:\/\/github.com\/mohmdelsayed\/streaming-drl<\/section>\n<\/li>\n<li>\n<section>\u8bba\u6587\u6807\u9898\uff1aDeep Reinforcement Learning Without Experience Replay, Target Networks, or Batch Updates<\/section>\n<\/li>\n<\/ul>\n<section><\/section>\n<section>\u8bba\u6587\u4f5c\u8005\u8fd8\u63d0\u4f9b\u4e86 stream-x \u7b97\u6cd5\u7684\u6700\u5c0f\u5b9e\u73b0\uff08\u5927\u7ea6 150 \u884c\u4ee3\u7801\uff09\uff0c\u611f\u5174\u8da3\u7684\u8bfb\u8005\u53ef\u4ee5\u53c2\u8003\u539f\u9879\u76ee\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-067be4c42631c1b87a6ca824be68835b.gif\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-067be4c42631c1b87a6ca824be68835b.gif\"><\/a><\/section>\n<section>\u672c\u6587\u8bc1\u660e\u4e86 stream-x \u7b97\u6cd5\u80fd\u591f\u514b\u670d\u6d41\u5f0f\u969c\u788d\u3002<\/section>\n<section><\/section>\n<section>\u5728\u7535\u529b\u6d88\u8017\u9884\u6d4b\u4efb\u52a1\u3001MuJoCo Gym\u3001DM Control Suite\u3001MinAtar \u548c Atari 2600 \u4e0a\u7684\u7ed3\u679c\u8bc1\u660e\uff0c\u8be5\u65b9\u6cd5\u80fd\u591f\u4f5c\u4e3a\u73b0\u6210\u7684\u89e3\u51b3\u65b9\u6848\uff0c\u514b\u670d\u6d41\u5f0f\u969c\u788d\uff0c\u63d0\u4f9b\u4ee5\u524d\u65e0\u6cd5\u901a\u8fc7\u6d41\u5f0f\u65b9\u6cd5\u5b9e\u73b0\u7684\u7ed3\u679c\uff0c\u751a\u81f3\u8d85\u8d8a\u6279\u91cf RL \u7684\u6027\u80fd\u3002\u7279\u522b\u662f\uff0cstream AC \u7b97\u6cd5\u5728\u4e00\u4e9b\u590d\u6742\u7684\u73af\u5883\u4e2d\u8fbe\u5230\u4e86\u5df2\u77e5\u7684\u6700\u4f73\u6027\u80fd\u3002\u00a0<\/section>\n<section><\/section>\n<section>\u5982\u4e0b\u6240\u793a\uff0c\u7ecf\u5178\u7684\u6d41\u65b9\u6cd5\uff08\u4f8b\u5982 Classic Q \uff09\u548c\u6279\u5904\u7406 RL \u65b9\u6cd5\u7684\u6d41\u5f0f\u7248\u672c\uff08\u4f8b\u5982 PPO1\uff09\u7531\u4e8e\u6d41\u5f0f\u969c\u788d\u800c\u8868\u73b0\u4e0d\u4f73\u3002\u76f8\u6bd4\u4e4b\u4e0b\uff0c stream-x \u7b97\u6cd5\uff08\u4f8b\u5982 stream Q \uff09\u514b\u670d\u4e86\u6d41\u5f0f\u969c\u788d\uff0c\u5e76\u4e0e\u6279\u5904\u7406 RL \u7b97\u6cd5\u7ade\u4e89\uff0c\u8bc1\u660e\u4e86\u5176\u7a33\u5b9a\u6027\u548c\u9c81\u68d2\u6027\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-600dcb668d18948e900b49476b545ff2.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-600dcb668d18948e900b49476b545ff2.png\"><\/a><\/section>\n<section>\u8fd9\u9879\u7814\u7a76\u5f97\u5230\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236 Richard Sutton \u7684\u8f6c\u53d1\u548c\u8bc4\u8bba\uff1a<\/section>\n<section><\/section>\n<section>\u300c\u6700\u521d\u7684\u5f3a\u5316\u5b66\u4e60\uff08RL\uff09\u7b97\u6cd5\u53d7\u81ea\u7136\u5b66\u4e60\u7684\u542f\u53d1\uff0c\u662f\u5728\u7ebf\u4e14\u589e\u91cf\u5f0f\u7684 \u2014\u2014 \u4e5f\u5c31\u662f\u8bf4\uff0c\u5b83\u4eec\u662f\u4ee5\u6d41\u7684\u65b9\u5f0f\u8fdb\u884c\u5b66\u4e60\u7684\uff0c\u6bcf\u5f53\u65b0\u7684\u7ecf\u9a8c\u589e\u91cf\u53d1\u751f\u65f6\u5c31\u5b66\u4e60\uff0c\u7136\u540e\u5c06\u5176\u4e22\u5f03\uff0c\u6c38\u4e0d\u518d\u6b21\u5904\u7406\u3002<\/section>\n<section><\/section>\n<section>\u6d41\u5f0f\u7b97\u6cd5\u7b80\u5355\u800c\u4f18\u96c5\uff0c\u4f46\u5728\u6df1\u5ea6\u5b66\u4e60\u4e2d\uff0cRL \u7684\u9996\u6b21\u91cd\u5927\u6210\u529f\u5e76\u975e\u6765\u81ea\u6d41\u5f0f\u7b97\u6cd5\u3002\u76f8\u53cd\uff0c\u50cf DQN\uff08\u6df1\u5ea6 Q \u7f51\u7edc\uff09\u8fd9\u6837\u7684\u65b9\u6cd5\u5c06\u7ecf\u9a8c\u6d41\u5207\u5272\u6210\u5355\u72ec\u7684\u8f6c\u6362\uff08transitions\uff09\uff0c\u7136\u540e\u4ee5\u4efb\u610f\u6279\u6b21\u8fdb\u884c\u5b58\u50a8\u548c\u91c7\u6837\u3002\u968f\u540e\u7684\u4e00\u7cfb\u5217\u5de5\u4f5c\u9075\u5faa\u3001\u6269\u5c55\u5e76\u5b8c\u5584\u4e86\u8fd9\u79cd\u6279\u91cf\u65b9\u6cd5\uff0c\u53d1\u5c55\u51fa\u5f02\u6b65\u548c\u79bb\u7ebf\u5f3a\u5316\u5b66\u4e60\uff0c\u800c\u6d41\u5f0f\u65b9\u6cd5\u5374\u505c\u6ede\u4e0d\u524d\uff0c\u65e0\u6cd5\u5728\u6d41\u884c\u7684\u6df1\u5ea6\u5b66\u4e60\u9886\u57df\u4e2d\u53d6\u5f97\u826f\u597d\u6548\u679c\u3002<\/section>\n<section><\/section>\n<section>\u76f4\u5230\u73b0\u5728\uff0c\u963f\u5c14\u4f2f\u5854\u5927\u5b66\u7684\u7814\u7a76\u4eba\u5458\u5df2\u7ecf\u8bc1\u660e\uff0c\u5728 Atari \u548c Mujoco \u4efb\u52a1\u4e0a\uff0c\u6d41\u5f0f\u5f3a\u5316\u5b66\u4e60\uff08Streaming RL\uff09 \u7b97\u6cd5\u53ef\u4ee5\u4e0e DQN \u4e00\u6837\u6709\u6548\u3002<\/section>\n<section><\/section>\n<section>\u5728\u6211\u770b\u6765\uff0c\u4ed6\u4eec\u4f3c\u4e4e\u662f\u7b2c\u4e00\u6279\u719f\u6089\u6d41\u5f0f\u5f3a\u5316\u5b66\u4e60\u7b97\u6cd5\u7684\u7814\u7a76\u4eba\u5458\uff0c\u8ba4\u771f\u5730\u89e3\u51b3\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u95ee\u9898\uff0c\u800c\u4e0d\u53d7\u6279\u91cf\u5bfc\u5411\u7684\u8f6f\u4ef6\u548c\u6279\u91cf\u5bfc\u5411\u7684\u76d1\u7763\u5b66\u4e60\u601d\u7ef4\u65b9\u5f0f\u7684\u8fc7\u5ea6\u5f71\u54cd\u3002\u300d<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-652a29428d888e8882ce2d8f6c8e0964.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-652a29428d888e8882ce2d8f6c8e0964.png\"><\/a><\/section>\n<section>\u8fd8\u6709\u7f51\u53cb\u8868\u793a\uff0c\u6d41\u5f0f\u7b97\u6cd5\u786e\u5b9e\u5851\u9020\u4e86\u5f3a\u5316\u5b66\u4e60\u7684\u683c\u5c40\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-8e1f00630eaedbb4ad2cc5159255b1b5.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-8e1f00630eaedbb4ad2cc5159255b1b5.png\"><\/a><\/section>\n<section><strong>\u65b9\u6cd5\u4ecb\u7ecd<\/strong><\/section>\n<section><\/section>\n<section>\u672c\u6587\u901a\u8fc7\u5f15\u5165\u6d41\u5f0f\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u65b9\u6cd5 \u2014\u2014Stream TD (\u03bb)\u3001Stream Q (\u03bb) \u548c Stream AC (\u03bb)\uff0c\u8fd9\u4e9b\u7edf\u79f0\u4e3a stream-x \u7b97\u6cd5\uff0c\u5e76\u5229\u7528\u8d44\u683c\u8ff9\uff0c\u6765\u89e3\u51b3\u6d41\u5f0f\u969c\u788d\u95ee\u9898\u3002<\/section>\n<section><\/section>\n<section>\u8be5\u65b9\u6cd5\u65e0\u9700\u4f7f\u7528\u91cd\u653e\u7f13\u51b2\u533a\u3001\u6279\u91cf\u66f4\u65b0\u6216\u76ee\u6807\u7f51\u7edc\uff0c\u5373\u53ef\u4ece\u6700\u65b0\u7684\u7ecf\u9a8c\u4e2d\u8fdb\u884c\u5b66\u4e60\u3002\u4e0e\u666e\u904d\u8ba4\u77e5\u76f8\u53cd\uff0c\u672c\u6587\u8bc1\u660e\u4e86\u6d41\u5f0f\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u53ef\u4ee5\u662f\u7a33\u5b9a\u7684\uff0c\u5e76\u4e14\u5728\u6837\u672c\u6548\u7387\u4e0a\u53ef\u4e0e\u6279\u91cf\u5f3a\u5316\u5b66\u4e60\u76f8\u5f53\u3002\u00a0<\/section>\n<section><\/section>\n<section>\u7531\u4e8e\u6d41\u5f0f\u5b66\u4e60\u65b9\u6cd5\u5728\u4f7f\u7528\u6837\u672c\u540e\u5fc5\u987b\u5c06\u5176\u4e22\u5f03\uff0c\u56e0\u6b64\u53ef\u80fd\u4f1a\u5bfc\u81f4\u6837\u672c\u6548\u7387\u4f4e\u4e0b\u3002\u4e3a\u6b64\uff0c\u672c\u6587\u63d0\u51fa\u4e86\u4e24\u79cd\u6280\u672f\u6765\u63d0\u9ad8\u6d41\u5f0f\u5b66\u4e60\u65b9\u6cd5\u7684\u6837\u672c\u6548\u7387\uff1a1\uff09\u7a00\u758f\u521d\u59cb\u5316\uff0c2\uff09\u8d44\u683c\u8ff9\u3002\u00a0<\/section>\n<section><\/section>\n<section>\u7b97\u6cd5 1 \u5c55\u793a\u4e86\u672c\u6587\u63d0\u51fa\u7684\u7a00\u758f\u521d\u59cb\u5316\u6280\u672f \u2014 SparseInit\u3002\u6b64\u7a00\u758f\u521d\u59cb\u5316\u65b9\u6848\u53ef\u7528\u4e8e\u5168\u8fde\u63a5\u5c42\u548c\u5377\u79ef\u5c42\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-dafd13475f76933d722c86662b216fb7.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-dafd13475f76933d722c86662b216fb7.png\"><\/a><\/section>\n<section>\u7b97\u6cd5 3 \u5c55\u793a\u4e86\u5982\u4f55\u6784\u5efa\u4e00\u4e2a\u4f18\u5316\u5668\uff0c\u8be5\u4f18\u5316\u5668\u4f7f\u7528\u6709\u6548\u6b65\u957f\u8fd9\u4e00\u6761\u4ef6\u6765\u63a7\u5236\u66f4\u65b0\u5927\u5c0f\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-18501771f11dfc6e6e3e507466d9d0da.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-18501771f11dfc6e6e3e507466d9d0da.png\"><\/a><\/section>\n<section>\u4e0b\u9762\u4e3a stream-x \u7b97\u6cd5\u4f2a\u4ee3\u7801\u3002\u4e3a\u4e86\u63d0\u9ad8\u7b97\u6cd5\u53ef\u8bfb\u6027\uff0c\u4f5c\u8005\u4f7f\u7528\u4e86\u4ee5\u4e0b\u989c\u8272\u7f16\u7801\uff1a\u7d2b\u8272\u8868\u793a\u5c42\u5f52\u4e00\u5316\uff0c\u84dd\u8272\u8868\u793a\u89c2\u6d4b\u89c4\u4e00\u5316\uff0c\u6a59\u8272\u8868\u793a\u5956\u52b1\u7f29\u653e\uff0c\u9752\u8272\u8868\u793a\u6b65\u957f\u7f29\u653e\uff0c\u68d5\u8272\u8868\u793a\u7a00\u758f\u521d\u59cb\u5316\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-dc2912dbe92f164a280a3289a85154f8.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-dc2912dbe92f164a280a3289a85154f8.png\"><\/a><\/section>\n<section><strong><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-15208a31ce48ad276d7e46467e5880ac.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-15208a31ce48ad276d7e46467e5880ac.png\"><\/a><\/strong><\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-cb85d85d2ac378bfbda81000f3b55bb1.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-cb85d85d2ac378bfbda81000f3b55bb1.png\"><\/a><\/section>\n<section><strong>\u5b9e\u9a8c\u7ed3\u679c<\/strong><\/section>\n<section><\/section>\n<section>\u4e3a\u4e86\u6f14\u793a Stream-x \u7b97\u6cd5\u7684\u6709\u6548\u6027\uff0c\u8be5\u7814\u7a76\u9996\u5148\u5c55\u793a\u4e86\u5728\u4e0d\u540c\u73af\u5883\u4e2d\u7ecf\u5178\u65b9\u6cd5\u5931\u8d25\u7684\u6d41\u5f0f\u969c\u788d\uff0c\u800c Stream-x \u7b97\u6cd5\u514b\u670d\u4e86\u8fd9\u4e00\u969c\u788d\uff0c\u5e76\u4e14\u4e0e\u5176\u4ed6\u6279\u5904\u7406\u65b9\u6cd5\u6027\u80fd\u76f8\u5f53\u3002<\/section>\n<section><\/section>\n<section><strong>\u514b\u670d\u6d41\u5f0f\u969c\u788d<\/strong><\/section>\n<section><\/section>\n<section>\u6d41\u5f0f\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u65b9\u6cd5\u7ecf\u5e38\u4f1a\u9047\u5230\u4e0d\u7a33\u5b9a\u548c\u5b66\u4e60\u5931\u8d25\u7684\u60c5\u51b5\uff0c\u79f0\u4e3a\u6d41\u5f0f\u969c\u788d\u3002\u56fe 2 \u663e\u793a\u4e86\u4e09\u4e2a\u4e0d\u540c\u7684\u5177\u6709\u6311\u6218\u6027\u7684\u57fa\u51c6\u6d4b\u8bd5\u4efb\u52a1\u4e2d\u7684\u6d41\u969c\u788d\uff1aMuJoCo\u3001DM Control \u548c Atari\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-41d7fdb4c212479fedbf76acdaf769c0.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-41d7fdb4c212479fedbf76acdaf769c0.png\"><\/a><\/section>\n<section><strong>Stream-x \u7b97\u6cd5\u7684\u6837\u672c\u6548\u7387<\/strong><\/section>\n<section><\/section>\n<section>\u8be5\u7814\u7a76\u901a\u8fc7\u6bd4\u8f83\u4e0d\u540c\u7b97\u6cd5\u7684\u5b66\u4e60\u66f2\u7ebf\u6765\u7814\u7a76 stream-x \u65b9\u6cd5\u7684\u6837\u672c\u6548\u7387\u3002\u56fe 3 \u663e\u793a\u4e86\u4e0d\u540c\u6df1\u5ea6 RL \u65b9\u6cd5\u5728\u56db\u4e2a\u8fde\u7eed\u63a7\u5236 MuJoCo \u4efb\u52a1\u4e0a\u7684\u6027\u80fd\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-aa4d4c058f7384ed070a8536750d20d4.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-aa4d4c058f7384ed070a8536750d20d4.png\"><\/a><\/section>\n<section>\u56fe 4 \u5c55\u793a\u4e86\u6d41 Q (0.8) \u4e0e\u5176\u5bf9\u5e94\u7ecf\u5178\u65b9\u6cd5\u4ee5\u53ca DQN1 \u548c DQN \u5728 MinAtar \u4efb\u52a1\u4e0a\u7684\u6027\u80fd\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-21fd73a80869dec26c3c41587edee815.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-21fd73a80869dec26c3c41587edee815.png\"><\/a><\/section>\n<section><strong>Stream-x \u7b97\u6cd5\u5728\u6269\u5c55\u8fd0\u884c\u4e2d\u7684\u7a33\u5b9a\u6027\u00a0<\/strong><\/section>\n<section><\/section>\n<section>\u63a5\u4e0b\u6765\uff0c\u7814\u7a76\u56e2\u961f\u63a2\u7a76\u4e86 Stream-x \u7b97\u6cd5\u5728\u957f\u65f6\u95f4\u8fd0\u884c\u65f6\u7684\u7a33\u5b9a\u6027\uff0c\u4ee5\u6709\u6548\u5730\u63ed\u793a\u65b9\u6cd5\u662f\u5426\u53ef\u4ee5\u957f\u65f6\u95f4\u8fd0\u884c\u800c\u4e0d\u51fa\u73b0\u4efb\u4f55\u95ee\u9898\u3002\u5b9e\u9a8c\u7ed3\u679c\u5982\u4e0b\u56fe 5 \u6240\u793a\uff1a<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-b211d245b29d251931b627d65a9257e4.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-b211d245b29d251931b627d65a9257e4.png\"><\/a><\/section>\n<section>\u56fe 6 \u663e\u793a\u4e86\u4e0d\u540c\u667a\u80fd\u4f53\u5728\u603b\u5171\u7ecf\u5386 2 \u4ebf\u5e27\u7684 Atari \u6e38\u620f\u4e0a\u7684\u6027\u80fd\uff1a<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-22cd3cabecce05ef0810aacf5e4e0b8c.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-22cd3cabecce05ef0810aacf5e4e0b8c.png\"><\/a><\/section>\n<section>\u611f\u5174\u8da3\u7684\u8bfb\u8005\u53ef\u4ee5\u9605\u8bfb\u8bba\u6587\u539f\u6587\uff0c\u4e86\u89e3\u66f4\u591a\u7814\u7a76\u5185\u5bb9\u3002<\/section>\n<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2024-11-29-7\" target=\"_blank\">\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[27],"tags":[65],"class_list":["post-36896","post","type-post","status-publish","format-standard","hentry","category-news","tag-65"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350 - \u4e00\u8d77AI\u6280\u672f<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/17aitech.com\/?p=36896\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896\"},\"author\":{\"name\":\"AI\u5c0f\u52a9\u624b\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/#\\\/schema\\\/person\\\/60225458499e817ae0af73e67e440b9d\"},\"headline\":\"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350\",\"datePublished\":\"2025-01-20T11:00:24+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896\"},\"wordCount\":93,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/frc-f5c534d6ffe06dacee7027c874265724.png\",\"keywords\":[\"\u6df1\u5ea6\u5b66\u4e60\"],\"articleSection\":[\"\u884c\u4e1a\u8d44\u8baf\"],\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/17aitech.com\\\/?p=36896#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896\",\"url\":\"https:\\\/\\\/17aitech.com\\\/?p=36896\",\"name\":\"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350 - \u4e00\u8d77AI\u6280\u672f\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/frc-f5c534d6ffe06dacee7027c874265724.png\",\"datePublished\":\"2025-01-20T11:00:24+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/#\\\/schema\\\/person\\\/60225458499e817ae0af73e67e440b9d\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/17aitech.com\\\/?p=36896\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#primaryimage\",\"url\":\"https:\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/frc-f5c534d6ffe06dacee7027c874265724.png\",\"contentUrl\":\"https:\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/11\\\/frc-f5c534d6ffe06dacee7027c874265724.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/?p=36896#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\\\/\\\/17aitech.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/#website\",\"url\":\"https:\\\/\\\/17aitech.com\\\/\",\"name\":\"\u4e00\u8d77AI\u6280\u672f\",\"description\":\"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca\",\"alternateName\":\"\u4e00\u8d77AI\u6280\u672f\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/17aitech.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/17aitech.com\\\/#\\\/schema\\\/person\\\/60225458499e817ae0af73e67e440b9d\",\"name\":\"AI\u5c0f\u52a9\u624b\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/robot_3.png\",\"url\":\"\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/robot_3.png\",\"contentUrl\":\"\\\/\\\/17aitech.com\\\/wp-content\\\/uploads\\\/2024\\\/04\\\/robot_3.png\",\"caption\":\"AI\u5c0f\u52a9\u624b\"},\"description\":\"\u8fd9\u4e2a\u4eba\u5f88\u61d2\uff0c\u4ec0\u4e48\u90fd\u6ca1\u6709\u7559\u4e0b\uff5e\",\"url\":\"https:\\\/\\\/17aitech.com\\\/?page_id=33738&user=3\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350 - \u4e00\u8d77AI\u6280\u672f","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/17aitech.com\/?p=36896","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/17aitech.com\/?p=36896#article","isPartOf":{"@id":"https:\/\/17aitech.com\/?p=36896"},"author":{"name":"AI\u5c0f\u52a9\u624b","@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d"},"headline":"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350","datePublished":"2025-01-20T11:00:24+00:00","mainEntityOfPage":{"@id":"https:\/\/17aitech.com\/?p=36896"},"wordCount":93,"commentCount":0,"image":{"@id":"https:\/\/17aitech.com\/?p=36896#primaryimage"},"thumbnailUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-f5c534d6ffe06dacee7027c874265724.png","keywords":["\u6df1\u5ea6\u5b66\u4e60"],"articleSection":["\u884c\u4e1a\u8d44\u8baf"],"inLanguage":"zh-Hans","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/17aitech.com\/?p=36896#respond"]}]},{"@type":"WebPage","@id":"https:\/\/17aitech.com\/?p=36896","url":"https:\/\/17aitech.com\/?p=36896","name":"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350 - \u4e00\u8d77AI\u6280\u672f","isPartOf":{"@id":"https:\/\/17aitech.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/17aitech.com\/?p=36896#primaryimage"},"image":{"@id":"https:\/\/17aitech.com\/?p=36896#primaryimage"},"thumbnailUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-f5c534d6ffe06dacee7027c874265724.png","datePublished":"2025-01-20T11:00:24+00:00","author":{"@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d"},"breadcrumb":{"@id":"https:\/\/17aitech.com\/?p=36896#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/17aitech.com\/?p=36896"]}]},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/?p=36896#primaryimage","url":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-f5c534d6ffe06dacee7027c874265724.png","contentUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/11\/frc-f5c534d6ffe06dacee7027c874265724.png"},{"@type":"BreadcrumbList","@id":"https:\/\/17aitech.com\/?p=36896#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/17aitech.com\/"},{"@type":"ListItem","position":2,"name":"\u6d41\u5f0f\u6df1\u5ea6\u5b66\u4e60\u7ec8\u4e8e\u594f\u6548\u4e86\uff01\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u529b\u8350"}]},{"@type":"WebSite","@id":"https:\/\/17aitech.com\/#website","url":"https:\/\/17aitech.com\/","name":"\u4e00\u8d77AI\u6280\u672f","description":"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca","alternateName":"\u4e00\u8d77AI\u6280\u672f","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/17aitech.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d","name":"AI\u5c0f\u52a9\u624b","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","url":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","contentUrl":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","caption":"AI\u5c0f\u52a9\u624b"},"description":"\u8fd9\u4e2a\u4eba\u5f88\u61d2\uff0c\u4ec0\u4e48\u90fd\u6ca1\u6709\u7559\u4e0b\uff5e","url":"https:\/\/17aitech.com\/?page_id=33738&user=3"}]}},"_links":{"self":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/36896","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=36896"}],"version-history":[{"count":0,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/36896\/revisions"}],"wp:attachment":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=36896"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=36896"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=36896"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}