arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.01506cs.LGcs.AI
收藏

国际象棋的神经网络

Neural Networks for Chess

Dominik Klein

摘要:

AlphaZero,Leela Chess Zero和Stockfish NNUE彻底改变了计算机国际象棋。这本书给出了一个完整的介绍到技术的内部工作这样的引擎。这本书分为四个主要章节-不包括第1章(介绍)和第6章(结论):第2章介绍了神经网络,并涵盖了用于构建深度网络的所有基本构建块,如AlphaZero使用的那些。内容包括感知器,反向传播和梯度下降,分类,回归,多层感知器,向量化技术,卷积网络,挤压和激励网络,全连接网络,批量归一化和整流线性单元,剩余层,过拟合和欠拟合。第3章介绍了用于国际象棋引擎的经典搜索技术以及AlphaZero使用的搜索技术。内容包括极大极小、α-β搜索和蒙特卡罗树搜索。第4章展示了现代国际象棋引擎是如何设计的。除了开创性的AlphaGo,AlphaGo Zero和AlphaZero之外,我们还包括Leela Chess Zero,Fat Fritz,Fat Fritz 2和高效可更新神经网络(NNUE)以及Maia。第5章是关于实现一个小型化的AlphaZero。Hexapawn是国际象棋的一个极简版本,被用作一个例子。Hexapawn通过极大极小搜索来求解,并生成用于监督学习的训练位置。然后,作为比较,实现了类似AlphaZero的训练循环,其中训练是通过与强化学习相结合的自我发挥来完成的。最后,比较了AlphaZero类训练和监督训练。

英文摘要:

AlphaZero, Leela Chess Zero and Stockfish NNUE revolutionized Computer Chess. This book gives a complete introduction into the technical inner workings of such engines. The book is split into four main chapters -- excluding chapter 1 (introduction) and chapter 6 (conclusion): Chapter 2 introduces neural networks and covers all the basic building blocks that are used to build deep networks such as those used by AlphaZero. Contents include the perceptron, back-propagation and gradient descent, classification, regression, multilayer perceptron, vectorization techniques, convolutional networks, squeeze and excitation networks, fully connected networks, batch normalization and rectified linear units, residual layers, overfitting and underfitting. Chapter 3 introduces classical search techniques used for chess engines as well as those used by AlphaZero. Contents include minimax, alpha-beta search, and Monte Carlo tree search. Chapter 4 shows how modern chess engines are designed. Aside from the ground-breaking AlphaGo, AlphaGo Zero and AlphaZero we cover Leela Chess Zero, Fat Fritz, Fat Fritz 2 and Efficiently Updatable Neural Networks (NNUE) as well as Maia. Chapter 5 is about implementing a miniaturized AlphaZero. Hexapawn, a minimalistic version of chess, is used as an example for that. Hexapawn is solved by minimax search and training positions for supervised learning are generated. Then as a comparison, an AlphaZero-like training loop is implemented where training is done via self-play combined with reinforcement learning. Finally, AlphaZero-like training and supervised training are compared.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑