{"id":39222,"date":"2025-03-05T21:01:38","date_gmt":"2025-03-05T13:01:38","guid":{"rendered":"https:\/\/17aitech.com\/?p=39222"},"modified":"2025-03-05T21:01:38","modified_gmt":"2025-03-05T13:01:38","slug":"%e5%88%9a%e5%88%9a%ef%bc%8c2024%e5%9b%be%e7%81%b5%e5%a5%96%e9%a2%81%e7%bb%99%e4%ba%86%e5%bc%ba%e5%8c%96%e5%ad%a6%e4%b9%a0%e4%b9%8b%e7%88%b6richard-sutton%e4%b8%8e%e5%af%bc%e5%b8%88andrew-barto","status":"publish","type":"post","link":"https:\/\/17aitech.com\/?p=39222","title":{"rendered":"\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto"},"content":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2025-03-05-16\" target=\"_blank\">\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto<\/a><\/p>\n<blockquote data-author-name=\"\" data-content-utf8-length=\"51\" data-source-title=\"\" data-type=\"2\" data-url=\"\">\n<section>\n<section>\u5f3a\u5316\u5b66\u4e60\u5148\u9a71 Andrew Barto \u4e0e Richard Sutton \u83b7\u5f97\u4eca\u5e74\u7684 ACM \u56fe\u7075\u5956\u3002<\/section>\n<\/section>\n<\/blockquote>\n<section><\/section>\n<section>\u4eba\u5de5\u667a\u80fd\u5b66\u8005\uff0c\u518d\u6b21\u6536\u83b7\u56fe\u7075\u5956\uff01<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png\"><\/a><\/section>\n<section>\u521a\u521a\uff0c\u8ba1\u7b97\u673a\u5b66\u4f1a\uff08ACM\uff09\u5ba3\u5e03\u4e86 2024 \u5e74\u7684 ACM A.M. Turing Award\uff08\u56fe\u7075\u5956\uff09\u83b7\u5f97\u8005\uff1a<strong>Andrew Barto<\/strong> \u548c <strong>Richard Sutton<\/strong>\u3002<\/section>\n<section><\/section>\n<section>\u4ed6\u4eec\u90fd\u662f\u5bf9\u5f3a\u5316\u5b66\u4e60\u505a\u51fa\u5960\u57fa\u6027\u8d21\u732e\u7684\u8457\u540d\u7814\u7a76\u8005\uff0cRichard Sutton \u66f4\u662f\u6709\u300c\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236\u300d\u7684\u7f8e\u8a89\u3002Andrew Barto \u5219\u662f Sutton \u7684\u535a\u58eb\u5bfc\u5e08\u3002\u81ea 1980 \u5e74\u4ee3\u8d77\uff0c\u4e24\u4f4d\u5b66\u8005\u5728\u4e00\u7cfb\u5217\u8bba\u6587\u4e2d\u63d0\u51fa\u4e86\u5f3a\u5316\u5b66\u4e60\u7684\u4e3b\u8981\u601d\u60f3\uff0c\u8fd8\u6784\u5efa\u4e86\u5f3a\u5316\u5b66\u4e60\u7684\u6570\u5b66\u57fa\u7840\uff0c\u5e76\u5f00\u53d1\u4e86\u5f3a\u5316\u5b66\u4e60\u7684\u91cd\u8981\u7b97\u6cd5\u3002\u4e24\u4eba\u5408\u8457\u7684\u300a<strong>Reinforcement\u00a0Learning: An\u00a0Introduction<\/strong>\u300b\u4e00\u76f4\u662f\u5f3a\u5316\u5b66\u4e60\u9886\u57df\u6700\u7ecf\u5178\u7684\u6559\u6750\u4e4b\u4e00\u3002\u00a0<\/section>\n<section><\/section>\n<section>Andrew Barto \u662f\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u963f\u9ed8\u65af\u7279\u5206\u6821\u4fe1\u606f\u4e0e\u8ba1\u7b97\u673a\u79d1\u5b66\u8363\u4f11\u6559\u6388\u3002Richard Sutton \u662f\u963f\u5c14\u4f2f\u5854\u5927\u5b66\u8ba1\u7b97\u673a\u79d1\u5b66\u6559\u6388\uff0c\u540c\u65f6\u4e5f\u662f Keen Technologies \u7684\u7814\u7a76\u79d1\u5b66\u5bb6\u3002<\/section>\n<section><\/section>\n<section>ACM \u56fe\u7075\u5956\u5e38\u88ab\u79f0\u4e3a\u300c\u8ba1\u7b97\u673a\u9886\u57df\u7684\u8bfa\u8d1d\u5c14\u5956\u300d\uff0c\u5956\u91d1\u4e3a 100 \u4e07\u7f8e\u5143\uff0c\u7531\u8c37\u6b4c\u516c\u53f8\u63d0\u4f9b\u8d44\u91d1\u652f\u6301\u3002\u8be5\u5956\u9879\u4ee5\u63d0\u51fa\u8ba1\u7b97\u6570\u5b66\u57fa\u7840\u7684\u82f1\u56fd\u6570\u5b66\u5bb6\u827e\u4f26\u30fb\u56fe\u7075\u547d\u540d\u3002<\/section>\n<section><\/section>\n<section><strong>\u5f3a\u5316\u5b66\u4e60\uff0c\u5f53\u4eca AI \u7a81\u7834\u7684\u539f\u70b9<\/strong><\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-61b351eb6af7330c1d3a1812d3161ff6.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-61b351eb6af7330c1d3a1812d3161ff6.png\"><\/a><\/section>\n<section>\u8bf4\u8d77\u5f3a\u5316\u5b66\u4e60\uff0c\u6211\u4eec\u53ef\u4ee5\u60f3\u8d77\u6700\u8fd1\u5f15\u7206\u5168\u7403 AI \u6280\u672f\u7206\u53d1\u7684 DeepSeek R1\uff0c\u5176\u4e2d\u7684\u5f3a\u5316\u5b66\u4e60\u7b97\u6cd5 GRPO \u8d4b\u4e88\u4e86\u5927\u6a21\u578b\u6781\u5f3a\u7684\u63a8\u7406\u80fd\u529b\uff0c\u4e14\u4e0d\u9700\u8981\u5927\u91cf\u76d1\u7763\u5fae\u8c03\uff0c\u662f AI \u6027\u80fd\u7a81\u7834\u7684\u6838\u5fc3\u3002<\/section>\n<section><\/section>\n<section>\u518d\u5f80\u524d\u770b\uff0c\u5728\u56f4\u68cb\u4e0a\u8d85\u8d8a\u4eba\u7c7b\u7684 AlphaGo \u4e5f\u662f\u5229\u7528\u5f3a\u5316\u5b66\u4e60\u81ea\u6211\u535a\u5f08\u8bad\u7ec3\u51fa\u7684\u7b56\u7565\u3002\u53ef\u4ee5\u8bf4\u6700\u8fd1\u7684\u51e0\u6b21 AI \u7a81\u7834\uff0c\u80cc\u540e\u603b\u6709\u5f3a\u5316\u5b66\u4e60\u7684\u8eab\u5f71\u3002<\/section>\n<section><\/section>\n<section>\u4eba\u5de5\u667a\u80fd\u9886\u57df\u901a\u5e38\u4f1a\u6bd4\u8f83\u5173\u6ce8\u667a\u80fd\u4f53\u7684\u6784\u5efa \u2014\u2014 \u5373\u53ef\u4ee5\u611f\u77e5\u548c\u884c\u52a8\u7684\u5b9e\u4f53\u3002\u66f4\u667a\u80fd\u7684\u667a\u80fd\u4f53\u80fd\u591f\u9009\u62e9\u66f4\u597d\u7684\u884c\u52a8\u65b9\u6848\u3002\u56e0\u6b64\uff0c\u60f3\u51fa\u6bd4\u5176\u4ed6\u65b9\u6848\u66f4\u597d\u884c\u52a8\u65b9\u6848\u6982\u5ff5\uff0c\u5bf9 AI \u975e\u5e38\u5173\u952e\u3002\u501f\u7528\u81ea\u5fc3\u7406\u5b66\u548c\u795e\u7ecf\u79d1\u5b66\u7684\u300c\u5956\u52b1\u300d\u2014 \u8bcd\uff0c\u8868\u793a\u5411\u667a\u80fd\u4f53\u63d0\u4f9b\u7684\u4e0e\u5176\u884c\u4e3a\u8d28\u91cf\u76f8\u5173\u7684\u4fe1\u53f7\u3002\u5f3a\u5316\u5b66\u4e60\uff08RL\uff09\u662f\u5728\u8fd9\u79cd\u4fe1\u53f7\u4e0b\u5b66\u4e60\u66f4\u6210\u529f\u884c\u4e3a\u7684\u8fc7\u7a0b\u3002<\/section>\n<section><\/section>\n<section>\u901a\u8fc7\u5956\u52b1\u5b66\u4e60\u7684\u7406\u5ff5\u5bf9\u52a8\u7269\u8bad\u7ec3\u5e08\u6765\u8bf4\u5df2\u6709\u6570\u5343\u5e74\u5386\u53f2\u3002\u540e\u6765\uff0c\u827e\u4f26\u30fb\u56fe\u7075 1950 \u5e74\u7684\u8bba\u6587\u300a\u8ba1\u7b97\u673a\u68b0\u4e0e\u667a\u80fd\u300b\u63d0\u51fa\u4e86\u300c\u673a\u5668\u80fd\u601d\u8003\u5417\uff1f\u300d\u7684\u95ee\u9898\uff0c\u5e76\u63d0\u51fa\u4e86\u57fa\u4e8e\u5956\u52b1\u548c\u60e9\u7f5a\u7684\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u3002<\/section>\n<section><\/section>\n<section>\u56fe\u7075\u62a5\u544a\u8bf4\u4ed6\u8fdb\u884c\u4e86\u4e00\u4e9b\u521d\u6b65\u5b9e\u9a8c\uff0cArthur Samuel \u4e5f\u5728 1950 \u5e74\u4ee3\u540e\u671f\u5f00\u53d1\u4e86\u4e00\u4e2a\u80fd\u901a\u8fc7\u81ea\u6211\u5bf9\u5f08\u5b66\u4e60\u7684\u8df3\u68cb\u7a0b\u5e8f\u3002\u4f46\u5728\u63a5\u4e0b\u6765\u7684\u51e0\u5341\u5e74\u91cc\uff0cAI \u7684\u8fd9\u4e00\u65b9\u5411\u8fdb\u5c55\u751a\u5fae\u3002<\/section>\n<section><\/section>\n<section>\u76f4\u81f3 1980 \u5e74\u4ee3\u521d\uff0c\u53d7\u5fc3\u7406\u5b66\u89c2\u5bdf\u7684\u542f\u53d1\uff0cAndrew Barto \u548c\u4ed6\u7684\u535a\u58eb\u751f Richard Sutton \u5f00\u59cb\u5c06\u5f3a\u5316\u5b66\u4e60\u4f5c\u4e3a\u4e00\u4e2a\u901a\u7528\u95ee\u9898\u6846\u67b6\u8fdb\u884c\u6784\u5efa\u3002<\/section>\n<section><\/section>\n<section>\u4ed6\u4eec\u501f\u9274\u4e86\u9a6c\u5c14\u53ef\u592b\u51b3\u7b56\u8fc7\u7a0b\uff08MDP\uff09\u63d0\u4f9b\u7684\u6570\u5b66\u57fa\u7840\uff0c\u5728\u8fd9\u4e2a\u6846\u67b6\u4e2d\uff0c\u667a\u80fd\u4f53\u5728\u968f\u673a\u73af\u5883\u4e2d\u505a\u51fa\u51b3\u7b56\uff0c\u6bcf\u6b21\u8f6c\u6362\u540e\u6536\u5230\u5956\u52b1\u4fe1\u53f7\uff0c\u5e76\u6700\u5927\u5316\u5176\u957f\u671f\u7d2f\u79ef\u5956\u52b1\u3002<\/section>\n<section><\/section>\n<section>\u4e0e\u6807\u51c6 MDP \u7406\u8bba\u5047\u8bbe\u667a\u80fd\u4f53\u77e5\u9053\u4e00\u5207\u4e0d\u540c\uff0cRL \u6846\u67b6\u5141\u8bb8\u73af\u5883\u548c\u5956\u52b1\u662f\u672a\u77e5\u7684\u3002RL \u7684\u6700\u5c0f\u4fe1\u606f\u9700\u6c42\uff0c\u7ed3\u5408 MDP \u6846\u67b6\u7684\u901a\u7528\u6027\uff0c\u4f7f RL \u7b97\u6cd5\u53ef\u4ee5\u5e94\u7528\u4e8e\u5e7f\u6cdb\u7684\u95ee\u9898\u3002<\/section>\n<section><\/section>\n<section>Andrew Barto \u548c Richard Sutton \u8054\u624b\u6216\u8005\u534f\u540c\u4ed6\u4eba\uff0c\u90fd\u5f00\u53d1\u4e86\u8bb8\u591a RL \u57fa\u672c\u7b97\u6cd5\u3002\u5176\u4e2d\u5305\u62ec\u4ed6\u4eec\u6700\u91cd\u8981\u7684\u8d21\u732e \u2014\u2014 \u65f6\u95f4\u5dee\u5206\u5b66\u4e60\uff08\u8be5\u7b97\u6cd5\u4e3a\u89e3\u51b3\u5956\u52b1\u9884\u6d4b\u95ee\u9898\u53d6\u5f97\u4e86\u91cd\u8981\u8fdb\u5c55\uff09\uff0c\u4ee5\u53ca\u7b56\u7565\u68af\u5ea6\u65b9\u6cd5\u548c\u4f7f\u7528\u795e\u7ecf\u7f51\u7edc\u4f5c\u4e3a\u8868\u793a\u5b66\u4e60\u51fd\u6570\u7684\u5de5\u5177\u3002\u4ed6\u4eec\u8fd8\u63d0\u51fa\u4e86\u7ed3\u5408\u5b66\u4e60\u548c\u89c4\u5212\u7684\u667a\u80fd\u4f53\u8bbe\u8ba1\uff0c\u5c55\u793a\u4e86\u83b7\u53d6\u73af\u5883\u77e5\u8bc6\u4f5c\u4e3a\u89c4\u5212\u57fa\u7840\u7684\u4ef7\u503c\u3002<\/section>\n<section><\/section>\n<section>\u540c\u6837\u6709\u5f71\u54cd\u529b\u7684\u662f\u4ed6\u4eec\u7684\u6559\u79d1\u4e66\u300aReinforcement Learning: An Introduction\u300b(1998)\uff0c\u5b83\u4ecd\u7136\u662f\u8be5\u9886\u57df\u7684\u6807\u51c6\u53c2\u8003\uff0c\u88ab\u5f15\u7528\u8d85\u8fc7 79,000 \u6b21\u3002\u8fd9\u672c\u4e66\u8ba9\u6570\u5343\u540d\u7814\u7a76\u4eba\u5458\u7406\u89e3\u5e76\u4e3a\u8fd9\u4e00\u65b0\u5174\u9886\u57df\u505a\u51fa\u8d21\u732e\uff0c\u81f3\u4eca\u4ecd\u6fc0\u53d1\u7740\u8ba1\u7b97\u673a\u79d1\u5b66\u9886\u57df\u7684\u8bb8\u591a\u91cd\u8981\u7814\u7a76\u6d3b\u52a8\u3002<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-edfdefad74fee736d2019d49aa591b6d.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-edfdefad74fee736d2019d49aa591b6d.png\"><\/a><\/section>\n<section>\u5c3d\u7ba1 Barto \u548c Sutton \u7684\u7b97\u6cd5\u662f\u6570\u5341\u5e74\u524d\u5f00\u53d1\u7684\uff0c\u4f46\u901a\u8fc7\u5c06\u5f3a\u5316\u5b66\u4e60\u4e0e\u6df1\u5ea6\u5b66\u4e60\uff08\u7531 2018 \u5e74\u56fe\u7075\u5956\u83b7\u5f97\u8005 Bengio\u3001Hinton\u3001LeCun \u5f00\u521b\uff09\u76f8\u7ed3\u5408\uff0c\u5f3a\u5316\u5b66\u4e60\u7684\u5b9e\u9645\u5e94\u7528\u5df2\u5728\u8fc7\u53bb\u5341\u4e94\u5e74\u4e2d\u53d6\u5f97\u91cd\u5927\u8fdb\u5c55\u3002\u4e8e\u662f\uff0c\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u6280\u672f\u5e94\u8fd0\u800c\u751f\u3002<\/section>\n<section><\/section>\n<section>\u5f3a\u5316\u5b66\u4e60\u6700\u8457\u540d\u7684\u4f8b\u5b50\u662f AlphaGo \u8ba1\u7b97\u673a\u7a0b\u5e8f\u5728 2016 \u5e74\u548c 2017 \u5e74\u6218\u80dc\u4e86\u9876\u7ea7\u4eba\u7c7b\u56f4\u68cb\u9009\u624b\u3002\u53e6\u4e00\u4e2a\u8fd1\u671f\u91cd\u5927\u6210\u5c31\u662f\u804a\u5929\u673a\u5668\u4eba ChatGPT\u3002<\/section>\n<section><\/section>\n<section>ChatGPT \u662f\u4e00\u4e2a\u7ecf\u8fc7\u4e24\u9636\u6bb5\u8bad\u7ec3\u5f97\u5230\u7684\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08LLM\uff09\uff0c\u5176\u4e2d\u7b2c\u4e8c\u9636\u6bb5\u91c7\u7528\u4e86\u4e00\u79cd\u540d\u4e3a\u300c\u57fa\u4e8e\u4eba\u7c7b\u53cd\u9988\u7684\u5f3a\u5316\u5b66\u4e60\uff08RLHF\uff09\u300d\u7684\u6280\u672f\uff0c\u5176\u4f5c\u7528\u662f\u53ef\u4ee5\u8ba9\u6a21\u578b\u8f93\u51fa\u7b26\u5408\u4eba\u7c7b\u671f\u671b\u3002<\/section>\n<section><\/section>\n<section>\u5f3a\u5316\u5b66\u4e60\u5728\u8bb8\u591a\u5176\u4ed6\u9886\u57df\u4e5f\u53d6\u5f97\u4e86\u6210\u529f\uff0c\u5176\u4e2d\u4e4b\u4e00\u662f\u673a\u5668\u4eba\u8fd0\u52a8\u6280\u80fd\u5b66\u4e60\u3002\u901a\u8fc7\u5f3a\u5316\u5b66\u4e60\uff0c\u673a\u5668\u624b\u53ef\u4ee5\u5b66\u4f1a\u64cd\u4f5c\u7269\u4f53\u548c\u89e3\u51b3\u7269\u7406\u95ee\u9898\uff1b\u5e76\u4e14\u8fd9\u79cd\u5b66\u4e60\u8fc7\u7a0b\u53ef\u5728\u6a21\u62df\u4e2d\u5b8c\u6210\uff0c\u7136\u540e\u518d\u8fc1\u79fb\u5230\u73b0\u5b9e\u4e16\u754c\u3002<\/section>\n<section><\/section>\n<section>\u5f3a\u5316\u5b66\u4e60\u9002\u7528\u7684\u9886\u57df\u8fd8\u5305\u62ec\u7f51\u7edc\u62e5\u5835\u63a7\u5236\u3001\u82af\u7247\u8bbe\u8ba1\u3001\u4e92\u8054\u7f51\u5e7f\u544a\u3001\u4f18\u5316\u3001\u5168\u7403\u4f9b\u5e94\u94fe\u4f18\u5316\u3001\u6539\u8fdb\u804a\u5929\u673a\u5668\u4eba\u7684\u884c\u4e3a\u548c\u63a8\u7406\u80fd\u529b\uff0c\u751a\u81f3\u6539\u8fdb\u77e9\u9635\u4e58\u6cd5\u7b97\u6cd5 \u2014\u2014 \u8fd9\u662f\u8ba1\u7b97\u673a\u79d1\u5b66\u4e2d\u6700\u53e4\u8001\u7684\u95ee\u9898\u4e4b\u4e00\u3002<\/section>\n<section><\/section>\n<section>\u6700\u540e\uff0c\u5f3a\u5316\u5b66\u4e60\u8fd8\u53cd\u8fc7\u6765\u52a9\u529b\u4e86\u795e\u7ecf\u79d1\u5b66\u7684\u53d1\u5c55 \u2014\u2014 \u5f3a\u5316\u5b66\u4e60\u6b63\u662f\u53d7\u5230\u4e86\u8be5\u5b66\u79d1\u7684\u542f\u53d1\u3002\u6700\u8fd1\u7684\u7814\u7a76\uff0c\u5305\u62ec Barto \u7684\u7814\u7a76\u6210\u679c\uff0c\u5df2\u7ecf\u8868\u660e AI \u9886\u57df\u5f00\u53d1\u7684\u67d0\u4e9b\u5f3a\u5316\u5b66\u4e60\u7b97\u6cd5\u53ef\u4e3a\u6d89\u53ca\u4eba\u7c7b\u5927\u8111\u4e2d\u591a\u5df4\u80fa\u7cfb\u7edf\u7684\u5e7f\u6cdb\u53d1\u73b0\u63d0\u4f9b\u6700\u4f73\u89e3\u91ca\u3002<\/section>\n<section><\/section>\n<section>\u300cBarto \u548c Sutton \u7684\u5de5\u4f5c\u5c55\u793a\u4e86\u5c06\u591a\u5b66\u79d1\u65b9\u6cd5\u5e94\u7528\u4e8e\u6211\u4eec\u9886\u57df\u957f\u671f\u6311\u6218\u7684\u5de8\u5927\u6f5c\u529b\uff0c\u300dACM \u4e3b\u5e2d Yannis Ioannidis \u89e3\u91ca\u9053\u3002\u300c\u4ece\u8ba4\u77e5\u79d1\u5b66\u548c\u5fc3\u7406\u5b66\u5230\u795e\u7ecf\u79d1\u5b66\u7684\u7814\u7a76\u9886\u57df\u542f\u53d1\u4e86\u5f3a\u5316\u5b66\u4e60\u7684\u53d1\u5c55\uff0c\u8fd9\u4e3a AI \u9886\u57df\u7684\u4e00\u4e9b\u6700\u91cd\u8981\u8fdb\u5c55\u5960\u5b9a\u4e86\u57fa\u7840\uff0c\u5e76\u8ba9\u6211\u4eec\u66f4\u6df1\u5165\u5730\u4e86\u89e3\u5927\u8111\u5982\u4f55\u5de5\u4f5c\u3002Barto \u548c Sutton \u7684\u5de5\u4f5c\u4e0d\u662f\u6211\u4eec\u5df2\u7ecf\u8d85\u8d8a\u7684\u57ab\u811a\u77f3\u3002\u5f3a\u5316\u5b66\u4e60\u7ee7\u7eed\u53d1\u5c55\uff0c\u5e76\u4e3a\u8ba1\u7b97\u548c\u8bb8\u591a\u5176\u4ed6\u5b66\u79d1\u7684\u8fdb\u4e00\u6b65\u53d1\u5c55\u63d0\u4f9b\u4e86\u5de8\u5927\u6f5c\u529b\u3002\u7528\u6211\u4eec\u9886\u57df\u6700\u8d1f\u76db\u540d\u7684\u5956\u9879\u8868\u5f70\u4ed6\u4eec\u662f\u975e\u5e38\u6070\u5f53\u7684\u3002\u300d<\/section>\n<section><\/section>\n<section>\u300c\u5728 1947 \u5e74\u7684\u4e00\u6b21\u6f14\u8bb2\u4e2d\uff0c\u827e\u4f26\u30fb\u56fe\u7075\u8868\u793a\u300e\u6211\u4eec\u60f3\u8981\u7684\u662f\u4e00\u53f0\u80fd\u4ece\u7ecf\u9a8c\u4e2d\u5b66\u4e60\u7684\u673a\u5668\u300f\u300d\uff0c\u8c37\u6b4c\u9ad8\u7ea7\u526f\u603b\u88c1 Jeff Dean \u6307\u51fa\u3002\u300cBarto \u548c Sutton \u5f00\u521b\u7684\u5f3a\u5316\u5b66\u4e60\u76f4\u63a5\u56de\u5e94\u4e86\u56fe\u7075\u7684\u6311\u6218\u3002\u4ed6\u4eec\u7684\u5de5\u4f5c\u662f\u8fc7\u53bb\u51e0\u5341\u5e74 AI \u8fdb\u6b65\u7684\u5173\u952e\u3002\u4ed6\u4eec\u5f00\u53d1\u7684\u5de5\u5177\u4ecd\u7136\u662f AI \u7e41\u8363\u7684\u4e2d\u5fc3\u652f\u67f1\uff0c\u5e26\u6765\u4e86\u91cd\u5927\u8fdb\u6b65\uff0c\u5438\u5f15\u4e86\u5927\u91cf\u5e74\u8f7b\u7814\u7a76\u4eba\u5458\uff0c\u5e76\u63a8\u52a8\u4e86\u6570\u5341\u4ebf\u7f8e\u5143\u7684\u6295\u8d44\u3002RL \u7684\u5f71\u54cd\u5c06\u6301\u7eed\u5230\u672a\u6765\u3002\u8c37\u6b4c\u5f88\u8363\u5e78\u8d5e\u52a9 ACM \u56fe\u7075\u5956\u5e76\u8868\u5f70\u90a3\u4e9b\u5851\u9020\u4e86\u6539\u5584\u6211\u4eec\u751f\u6d3b\u7684\u6280\u672f\u7684\u4e2a\u4eba\u3002\u300d<\/section>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-c48189d11b67071b3b92042b98d71204.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-c48189d11b67071b3b92042b98d71204.png\"><\/a><\/section>\n<section><strong>\u4e2a\u4eba\u80cc\u666f<\/strong><\/section>\n<section><strong>Andrew G. Barto<\/strong><\/section>\n<section><\/section>\n<section>Andrew Barto \u662f\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u963f\u9ed8\u65af\u7279\u5206\u6821\u4fe1\u606f\u4e0e\u8ba1\u7b97\u673a\u79d1\u5b66\u7cfb\u8363\u8a89\u9000\u4f11\u6559\u6388\u3002\u4ed6\u4e8e 1977 \u5e74\u4f5c\u4e3a\u535a\u58eb\u540e\u7814\u7a76\u52a9\u7406\u5728\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u963f\u9ed8\u65af\u7279\u5206\u6821\u5f00\u59cb\u804c\u4e1a\u751f\u6daf\uff0c\u6b64\u540e\u62c5\u4efb\u8fc7\u591a\u4e2a\u804c\u4f4d\uff0c\u5305\u62ec\u526f\u6559\u6388\u3001\u6559\u6388\u548c\u7cfb\u4e3b\u4efb\u3002Barto \u5728\u5bc6\u6b47\u6839\u5927\u5b66\u83b7\u5f97\u6570\u5b66\u5b66\u58eb\u5b66\u4f4d\uff08\u4f18\u7b49\uff09\uff0c\u5e76\u5728\u90a3\u91cc\u83b7\u5f97\u4e86\u8ba1\u7b97\u673a\u4e0e\u901a\u4fe1\u79d1\u5b66\u7684\u7855\u58eb\u548c\u535a\u58eb\u5b66\u4f4d\u3002<\/section>\n<section><\/section>\n<section>Barto \u7684\u8363\u8a89\u5305\u62ec\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u795e\u7ecf\u79d1\u5b66\u7ec8\u8eab\u6210\u5c31\u5956\u3001IJCAI \u7814\u7a76\u5353\u8d8a\u5956\uff08Research Excellence Award\uff09\u548c IEEE \u795e\u7ecf\u7f51\u7edc\u5b66\u4f1a\u5148\u9a71\u5956\u3002\u4ed6\u662f\u7535\u6c14\u548c\u7535\u5b50\u5de5\u7a0b\u5e08\u534f\u4f1a\uff08IEEE\uff09\u4f1a\u58eb\u548c\u7f8e\u56fd\u79d1\u5b66\u4fc3\u8fdb\u4f1a\uff08AAAS\uff09\u4f1a\u58eb\u3002<\/section>\n<section><\/section>\n<section><strong>Richard S. Sutton<\/strong><\/section>\n<section><\/section>\n<section>Richard S. Sutton \u662f\u963f\u5c14\u4f2f\u5854\u5927\u5b66\u8ba1\u7b97\u673a\u79d1\u5b66\u6559\u6388\u3001Keen Technologies\uff08\u4e00\u5bb6\u603b\u90e8\u4f4d\u4e8e\u5fb7\u514b\u8428\u65af\u5dde\u8fbe\u62c9\u65af\u7684\u901a\u7528\u4eba\u5de5\u667a\u80fd\u516c\u53f8\uff09\u7684\u7814\u7a76\u79d1\u5b66\u5bb6\uff0c\u4ee5\u53ca\u963f\u5c14\u4f2f\u5854\u673a\u5668\u667a\u80fd\u7814\u7a76\u6240\uff08Amii\uff09\u7684\u9996\u5e2d\u79d1\u5b66\u987e\u95ee\u3002Sutton \u4ece 2017 \u5e74\u5230 2023 \u5e74\u662f DeepMind \u7684\u6770\u51fa\u7814\u7a76\u79d1\u5b66\u5bb6\u3002\u5728\u52a0\u5165\u963f\u5c14\u4f2f\u5854\u5927\u5b66\u4e4b\u524d\uff0c\u4ed6\u66fe\u4e8e 1998 \u5e74\u81f3 2002 \u5e74\u5728\u65b0\u6cfd\u897f\u5dde Florham Park \u7684 AT&amp;T \u9999\u519c\u5b9e\u9a8c\u5ba4\u4eba\u5de5\u667a\u80fd\u90e8\u95e8\u62c5\u4efb\u9996\u5e2d\u6280\u672f\u4eba\u5458\u3002<\/section>\n<section><\/section>\n<section>Sutton \u4e0e Andrew Barto \u7684\u5408\u4f5c\u59cb\u4e8e 1978 \u5e74\uff0c\u5f53\u65f6\u5728\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u963f\u9ed8\u65af\u7279\u5206\u6821\uff0cBarto \u662f Sutton \u7684\u535a\u58eb\u548c\u535a\u58eb\u540e\u5bfc\u5e08\u3002Sutton \u5728\u65af\u5766\u798f\u5927\u5b66\u83b7\u5f97\u5fc3\u7406\u5b66\u5b66\u58eb\u5b66\u4f4d\uff0c\u5728\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u963f\u9ed8\u65af\u7279\u5206\u6821\u83b7\u5f97\u8ba1\u7b97\u673a\u4e0e\u4fe1\u606f\u79d1\u5b66\u7684\u7855\u58eb\u548c\u535a\u58eb\u5b66\u4f4d\u3002<\/section>\n<section><\/section>\n<section>Sutton \u7684\u8363\u8a89\u5305\u62ec\u83b7\u5f97 IJCAI \u7814\u7a76\u5353\u8d8a\u5956\u3001\u52a0\u62ff\u5927\u4eba\u5de5\u667a\u80fd\u534f\u4f1a\u7ec8\u8eab\u6210\u5c31\u5956\u548c\u9a6c\u8428\u8bf8\u585e\u5927\u5b66\u963f\u9ed8\u65af\u7279\u5206\u6821\u7684\u6770\u51fa\u7814\u7a76\u6210\u5c31\u5956\u3002Sutton \u662f\u4f26\u6566\u7687\u5bb6\u5b66\u4f1a\u4f1a\u58eb\u3001\u4eba\u5de5\u667a\u80fd\u4fc3\u8fdb\u534f\u4f1a\u4f1a\u58eb\u548c\u52a0\u62ff\u5927\u7687\u5bb6\u5b66\u4f1a\u4f1a\u58eb\u3002<\/section>\n<section><\/section>\n<section><em><sup>\u53c2\u8003\u94fe\u63a5<\/sup><\/em><\/section>\n<section><sup><em>https:\/\/x.com\/TheOfficialACM\/status\/1897225672935735579<\/em><\/sup><\/section>\n<section><em><sup>https:\/\/amturing.acm.org\/<\/sup><\/em><\/section>\n<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2025-03-05-16\" target=\"_blank\">\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881 [&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":[68,55,65],"class_list":["post-39222","post","type-post","status-publish","format-standard","hentry","category-news","tag-68","tag-55","tag-65"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto - \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=39222\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/17aitech.com\/?p=39222\",\"url\":\"https:\/\/17aitech.com\/?p=39222\",\"name\":\"\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto - \u4e00\u8d77AI\u6280\u672f\",\"isPartOf\":{\"@id\":\"https:\/\/17aitech.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/17aitech.com\/?p=39222#primaryimage\"},\"image\":{\"@id\":\"https:\/\/17aitech.com\/?p=39222#primaryimage\"},\"thumbnailUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png\",\"datePublished\":\"2025-03-05T13:01:38+00:00\",\"author\":{\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d\"},\"breadcrumb\":{\"@id\":\"https:\/\/17aitech.com\/?p=39222#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/17aitech.com\/?p=39222\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/?p=39222#primaryimage\",\"url\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png\",\"contentUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/17aitech.com\/?p=39222#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/17aitech.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto\"}]},{\"@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\":\"https:\/\/17aitech.com\/#\/schema\/person\/image\/\",\"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":"\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto - \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=39222","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/17aitech.com\/?p=39222","url":"https:\/\/17aitech.com\/?p=39222","name":"\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto - \u4e00\u8d77AI\u6280\u672f","isPartOf":{"@id":"https:\/\/17aitech.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/17aitech.com\/?p=39222#primaryimage"},"image":{"@id":"https:\/\/17aitech.com\/?p=39222#primaryimage"},"thumbnailUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png","datePublished":"2025-03-05T13:01:38+00:00","author":{"@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d"},"breadcrumb":{"@id":"https:\/\/17aitech.com\/?p=39222#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/17aitech.com\/?p=39222"]}]},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/?p=39222#primaryimage","url":"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png","contentUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2025\/03\/frc-633d70c829ee22be432312d2fcf84b18.png"},{"@type":"BreadcrumbList","@id":"https:\/\/17aitech.com\/?p=39222#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/17aitech.com\/"},{"@type":"ListItem","position":2,"name":"\u521a\u521a\uff0c2024\u56fe\u7075\u5956\u9881\u7ed9\u4e86\u5f3a\u5316\u5b66\u4e60\u4e4b\u7236Richard Sutton\u4e0e\u5bfc\u5e08Andrew Barto"}]},{"@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":"https:\/\/17aitech.com\/#\/schema\/person\/image\/","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\/39222","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=39222"}],"version-history":[{"count":0,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/39222\/revisions"}],"wp:attachment":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=39222"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=39222"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=39222"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}