将超人类AI与人类行为相结合：作为模型系统的国际象棋
Aligning Superhuman AI with Human Behavior: Chess as a Model System
摘要：
随着人工智能变得越来越智能-在某些情况下，实现了超人的性能-人类向算法学习和与算法合作的潜力越来越大。然而，人工智能系统处理问题的方式通常与人类的方式不同，因此可能无法解释，难以学习。弥合人类和人工智能之间差距的关键一步是对构成人类行为的粒度行为进行建模，而不是简单地匹配人类的总体表现。我们在一个在人工智能领域有着悠久历史的模型系统中追求这个目标：国际象棋。一个国际象棋选手的综合表现是随着他们在比赛过程中做出决定而展开的。每个技能水平的玩家在线玩的数亿游戏形成了丰富的数据源，这些决策及其确切的背景都被详细记录下来。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动作。我们开发并推出了Maia，这是一种在人类象棋游戏中训练的Alpha-Zero的定制版本，它可以比现有引擎更高的精度预测人类的动作，并且可以在预测特定技能水平的玩家以可调的方式做出决策时实现最大的准确性。对于预测人类下一步是否会犯大错的双重任务，我们开发了一个深度神经网络，它的表现明显优于竞争基线。综上所述，我们的研究结果表明，在设计人工智能系统时，首先要准确地建模粒度人类决策，并考虑到人类的协作，这是很有希望的。
英文摘要：
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 Alpha-Zero 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.
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。
