象棋-源码

上传者: 42117082 | 上传时间: 2021-04-29 10:38:59 | 文件大小: 10.08MB | 文件类型: ZIP
象棋 该项目的报告在pdf文件中(用法语编写)。 我编写了Shogi引擎部分以及MCTS和神经网络部分。 该项目旨在设计与DeepMind的AlphaZero相同模型的AI演奏将棋。 AlphaZero是一款能够玩围棋,象棋和将棋的AI,并且达到了超人的性能。 它结合了蒙特卡洛树搜索和神经网络,并通过自身操作以无监督的方式进行训练。 它只知道游戏规则,而没有其他先验知识。 AI只能通过自学来学习策略。 Shogi文件夹包含两个AI:A0Jr和SNN。 A0Jr是AlphaZero模型上的AI。 目的只是使AI能够做出连贯的动作。 但是我的计算能力太低,无法训练模型甚至无法达到这个中等目标(即使使用Google Colab的GPU)。 这就是为什么我然后尝试仅使用神经网络而不使用蒙特卡洛树搜索来设计一个更简单的模型的原因。 该模型位于文件夹SNN(简单神经网络)中。 我使用了几种技巧

文件下载

资源详情

[{"title":"( 36 个子文件 10.08MB ) 象棋-源码","children":[{"title":"ShogiNnetAI-main","children":[{"title":"README.md <span style='color:#111;'> 1.61KB </span>","children":null,"spread":false},{"title":"Shogi","children":[{"title":"A0Jr","children":[{"title":"shogi_nn.py <span style='color:#111;'> 4.35KB </span>","children":null,"spread":false},{"title":"shogi_engine.py <span style='color:#111;'> 45.78KB </span>","children":null,"spread":false},{"title":"mcts_nn.py <span style='color:#111;'> 14.55KB </span>","children":null,"spread":false},{"title":"encoding.py <span style='color:#111;'> 1.98KB </span>","children":null,"spread":false}],"spread":true},{"title":"SNN","children":[{"title":"play_shogi.py <span style='color:#111;'> 5.01KB </span>","children":null,"spread":false},{"title":"shogi_engine.py <span style='color:#111;'> 56.15KB </span>","children":null,"spread":false},{"title":"configuration.py <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"colab.py <span style='color:#111;'> 1.86KB </span>","children":null,"spread":false},{"title":"evaluateAI.py <span style='color:#111;'> 4.35KB </span>","children":null,"spread":false},{"title":"checkpoints","children":[{"title":"session1","children":[{"title":"runManager.json <span style='color:#111;'> 2.01KB </span>","children":null,"spread":false},{"title":"nnet100.pt <span style='color:#111;'> 4.22MB </span>","children":null,"spread":false},{"title":"stateCheckpoints.npy <span style='color:#111;'> 2.36MB </span>","children":null,"spread":false},{"title":"histories.npy <span style='color:#111;'> 1000.13KB </span>","children":null,"spread":false},{"title":"buffer.json <span style='color:#111;'> 15.73KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"snnAI.py <span style='color:#111;'> 3.29KB </span>","children":null,"spread":false},{"title":"nnet.py <span style='color:#111;'> 2.10KB </span>","children":null,"spread":false},{"title":"randomAI.py <span style='color:#111;'> 370B </span>","children":null,"spread":false},{"title":"encoding.py <span style='color:#111;'> 6.17KB </span>","children":null,"spread":false},{"title":"runManager.py <span style='color:#111;'> 8.79KB </span>","children":null,"spread":false},{"title":"jsonManager.py <span style='color:#111;'> 980B </span>","children":null,"spread":false},{"title":"trainNNet.py <span style='color:#111;'> 3.15KB </span>","children":null,"spread":false},{"title":"gameGenerator.py <span style='color:#111;'> 9.43KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"TicTacToe","children":[{"title":"game_engine.py <span style='color:#111;'> 3.30KB </span>","children":null,"spread":false},{"title":"configuration.py <span style='color:#111;'> 1.42KB </span>","children":null,"spread":false},{"title":"evaluateAI.py <span style='color:#111;'> 4.36KB </span>","children":null,"spread":false},{"title":"checkpoints","children":[{"title":"session1","children":[{"title":"nnet.pt <span style='color:#111;'> 666.57KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"snnAI.py <span style='color:#111;'> 2.72KB </span>","children":null,"spread":false},{"title":"nnet.py <span style='color:#111;'> 2.21KB </span>","children":null,"spread":false},{"title":"randomAI.py <span style='color:#111;'> 339B </span>","children":null,"spread":false},{"title":"encoding.py <span style='color:#111;'> 1007B </span>","children":null,"spread":false},{"title":"runManager.py <span style='color:#111;'> 7.47KB </span>","children":null,"spread":false},{"title":"jsonManager.py <span style='color:#111;'> 1.07KB </span>","children":null,"spread":false},{"title":"trainNNet.py <span style='color:#111;'> 3.21KB </span>","children":null,"spread":false},{"title":"gameGenerator.py <span style='color:#111;'> 5.04KB </span>","children":null,"spread":false}],"spread":false},{"title":"Shogi AI Report.pdf <span style='color:#111;'> 5.74MB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明