Aligning Superhuman AI with Human Behavior: Chess as a Model System
Aligning Superhuman AI with Human Behavior: Chess as a Model System
复制标题
将超人人工智能与人类行为结合起来：国际象棋作为模型系统
DOI：
10.1145/3394486.3403219
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Ashton Anderson
中科院分区：
文献类型：
--
作者：
Reid McIlroy;S. Sen;J. Kleinberg;Ashton Anderson
随着人工智能变得越来越智能-在某些情况下，实现超人的表现-人类向算法学习并与之合作的潜力越来越大。然而，人工智能系统处理问题的方式往往与人们处理问题的方式不同，因此可能无法解释，也很难学习。弥合人类和人工智能之间的这一差距的关键一步是对构成人类行为的细粒度行为进行建模，而不是简单地匹配人类的总体表现。我们在一个人工智能领域有着悠久历史的模型系统中追求这一目标：国际象棋。棋手的综合表现表现在他们在整个棋局过程中做出决定的过程中。不同技能水平的玩家在网上玩的数以亿计的游戏构成了丰富的数据来源，这些决定及其准确的背景被详细记录在其中。将现有的国际象棋引擎应用于这些数据，包括AlphaZero的开源实现，我们发现它们不能很好地预测人类的移动。我们开发并推出了Maia，这是一个定制的AlphaZero版本，训练在人类国际象棋游戏上，它预测人类走法的准确率比现有引擎高得多，并且当以可调的方式预测特定技能水平的玩家做出的决定时，可以实现最大的准确率。对于预测人类下一步是否会犯大错误的双重任务，我们开发了一个深度神经网络，它的表现远远超过竞争基线。综上所述，我们的结果表明，通过首先准确地对人类决策进行粒度建模，设计考虑到人类协作的人工智能系统是有很大希望的。
As artificial intelligence becomes increasingly intelligent---in some cases, achieving superhuman performance---there is growing potential for humans to learn from and collaborate with algorithms. However, the ways in which AI systems approach problems are often different from the ways people do, and thus may be uninterpretable and hard to learn from. A crucial step in bridging this gap between human and artificial intelligence is modeling the granular actions that constitute human behavior, rather than simply matching aggregate human performance. We pursue this goal in a model system with a long history in artificial intelligence: chess. The aggregate performance of a chess player unfolds as they make decisions over the course of a game. The hundreds of millions of games played online by players at every skill level form a rich source of data in which these decisions, and their exact context, are recorded in minute detail. Applying existing chess engines to this data, including an open-source implementation of AlphaZero, we find that they do not predict human moves well. We develop and introduce Maia, a customized version of AlphaZero trained on human chess games, that predicts human moves at a much higher accuracy than existing engines, and can achieve maximum accuracy when predicting decisions made by players at a specific skill level in a tuneable way. For a dual task of predicting whether a human will make a large mistake on the next move, we develop a deep neural network that significantly outperforms competitive baselines. Taken together, our results suggest that there is substantial promise in designing artificial intelligence systems with human collaboration in mind by first accurately modeling granular human decision-making.