“第三十一章 围棋国手”版本间的差异
来自cslt Wiki
(以“==教学资料== * 教学参考 * [http://aigraph.cslt.org/courses/30/course-30.pptx 课件] * 小清爱提问:机器翻译的原理是什么 [...”为内容创建页面) |
|||
(相同用户的9个中间修订版本未显示) | |||
第1行: | 第1行: | ||
==教学资料== | ==教学资料== | ||
− | * [[教学参考- | + | * [[教学参考-31|教学参考]] |
− | * [http://aigraph.cslt.org/courses/ | + | * [http://aigraph.cslt.org/courses/31/course-31.pptx 课件] |
− | * | + | * 小清爱提问:阿尔法狗和深蓝算法有什么不同? [https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247487271&idx=1&sn=34234ceb7f8d984f2dc7f78907380461&chksm=c30805e5f47f8cf3b9ea02162facc17ab90a5d60c28596721c35ceb1d780d5547f9f9f81db69&scene=178#rd] |
==扩展阅读== | ==扩展阅读== | ||
− | * | + | * 18个围棋故事 [https://www.sohu.com/a/329680063_495640] |
+ | * 围棋的历史典故和发展历史 [https://www.fengyungoschool.com/weiqi/weiqi_story_CHN.htm] | ||
+ | * 百度百科:中国围棋规则 [https://baike.baidu.com/item/%E4%B8%AD%E5%9B%BD%E5%9B%B4%E6%A3%8B%E8%A7%84%E5%88%99/5425065] | ||
+ | * 知乎:围棋的简单规则 [https://www.zhihu.com/question/38042128] | ||
+ | |||
+ | * AI100问:阿尔法狗和深蓝算法有什么不同? [http://aigraph.cslt.org/ai100/AI-100-30-AlphaGo和深蓝在算法上有什么不同.pdf] | ||
+ | * AI100问:AlphaZero是如何从零学习的? [http://aigraph.cslt.org/ai100/AI-100-54-AlphaGo Zero是如何从零学习的.pdf] | ||
+ | * AI100问:alphago是如何战胜人类的? [http://aigraph.cslt.org/ai100/AI-100-44-alphago是如何战胜人类的.pdf] | ||
+ | |||
* DeepMind AlphaGO [https://www.deepmind.com/research/highlighted-research/alphago] | * DeepMind AlphaGO [https://www.deepmind.com/research/highlighted-research/alphago] | ||
* 百度百科:AlphaGo [https://baike.baidu.com/item/%E9%98%BF%E5%B0%94%E6%B3%95%E5%9B%B4%E6%A3%8B/19319610] | * 百度百科:AlphaGo [https://baike.baidu.com/item/%E9%98%BF%E5%B0%94%E6%B3%95%E5%9B%B4%E6%A3%8B/19319610] | ||
+ | * 维基百科:Alpha Go [http://aigraph.cslt.org/courses/31/AlphaGo-zh.pdf][http://aigraph.cslt.org/courses/31/AlphaGo.pdf] | ||
+ | * 薛永红, 王洪鹏, 机器下棋的历史与启示——从“深蓝”到AlphaZero [http://html.rhhz.net/kjdb/20191913.htm] | ||
+ | * AlphaGo赢得首场人机对决奇点离人更近了? [https://m.21jingji.com/article/20160310/c699786ad54b0a23d9b5f4d448d2e33f.html] | ||
* Reconstructing Turing's "Paper Machine" [https://en.chessbase.com/post/reconstructing-turing-s-paper-machine] | * Reconstructing Turing's "Paper Machine" [https://en.chessbase.com/post/reconstructing-turing-s-paper-machine] | ||
+ | * 李世石神之一手 [https://baike.baidu.com/item/%E7%A5%9E%E4%B9%8B%E4%B8%80%E6%89%8B/19459116][https://sports.sina.com.cn/go/2022-03-11/doc-imcwipih7927962.shtml][https://www.zhihu.com/question/41338510] | ||
+ | |||
==视频展示== | ==视频展示== | ||
* 图灵的象棋程序[http://aigraph.cslt.org/courses/31/Turing-chess.mp4] | * 图灵的象棋程序[http://aigraph.cslt.org/courses/31/Turing-chess.mp4] | ||
+ | * Bilibili: 李世石神之一手[https://www.bilibili.com/video/BV1Qs411Q7oJ/] | ||
+ | * AlphaGo Movie[http://aigraph.cslt.org/courses/31/alphago-movie.mp4] | ||
==演示链接== | ==演示链接== | ||
− | * | + | |
+ | * Gomoku [https://gomoku.yjyao.com/] | ||
+ | |||
==开发者资源== | ==开发者资源== | ||
− | * | + | * BetaGo [*][https://github.com/maxpumperla/betago] |
− | * | + | * MiniGo [*][https://github.com/maxpumperla/betago] |
+ | * AlphaZero [*][https://github.com/suragnair/alpha-zero-general] | ||
+ | * 五子棋 [*][https://github.com/GuoYi0/alphaFive][https://github.com/junxiaosong/AlphaZero_Gomoku] | ||
+ | |||
+ | |||
==高级读者== | ==高级读者== | ||
− | * | + | * Silver D, Schrittwieser J, Simonyan K, et al. Mastering the game of go without human knowledge[J]. nature, 2017, 550(7676): 354-359. [https://discovery.ucl.ac.uk/id/eprint/10045895/1/agz_unformatted_nature.pdf] |
− | * | + | * Schrittwieser J, Antonoglou I, Hubert T, et al. Mastering atari, go, chess and shogi by planning with a learned model[J]. Nature, 2020, 588(7839): 604-609.[https://arxiv.org/pdf/1911.08265.pdf&lang=en] |
2023年8月13日 (日) 02:21的最后版本
教学资料
扩展阅读
- AI100问:阿尔法狗和深蓝算法有什么不同? [6]
- AI100问:AlphaZero是如何从零学习的? Zero是如何从零学习的.pdf
- AI100问:alphago是如何战胜人类的? [7]
- DeepMind AlphaGO [8]
- 百度百科:AlphaGo [9]
- 维基百科:Alpha Go [10][11]
- 薛永红, 王洪鹏, 机器下棋的历史与启示——从“深蓝”到AlphaZero [12]
- AlphaGo赢得首场人机对决奇点离人更近了? [13]
- Reconstructing Turing's "Paper Machine" [14]
- 李世石神之一手 [15][16][17]
视频展示
演示链接
- Gomoku [21]
开发者资源