arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.11602cs.AIcs.LGstat.ML
收藏

国际象棋AI:机器智能的竞争范例

Chess AI: Competing Paradigms for Machine Intelligence

ChessEd;Booth School of Business(布斯商学院);University of Chicago(芝加哥大学);Phillips Academy(菲利普斯学院)

Shiva Maharaj, Nick Polson, Alex Turk

摘要:

长期以来,残局研究一直是测试人类创造力和智力的工具。我们发现它们也可以作为测试机器能力的工具。两个领先的国际象棋引擎Stockfish和Leela Chess Zero(LCZero)在比赛中采用了截然不同的方法。我们使用Plaskett's Puzzle(20世纪70年代末著名的残局研究)来比较这两个引擎。我们的实验表明,Stockfish优于LCZero的难题。我们研究了引擎之间的算法差异,并将我们的观察结果作为仔细解释测试结果的基础。从人类如何解决国际象棋问题中汲取灵感,我们问机器是否可以拥有某种形式的想象力。在理论方面,我们描述了如何贝尔曼方程可能被应用到优化的概率获胜。最后,我们讨论了我们的工作对人工智能(AI)和人工通用智能(AGI)的影响,为未来的研究提出了可能的途径。

英文摘要:

Endgame studies have long served as a tool for testing human creativity and intelligence. We find that they can serve as a tool for testing machine ability as well. Two of the leading chess engines, Stockfish and Leela Chess Zero (LCZero), employ significantly different methods during play. We use Plaskett's Puzzle, a famous endgame study from the late 1970s, to compare the two engines. Our experiments show that Stockfish outperforms LCZero on the puzzle. We examine the algorithmic differences between the engines and use our observations as a basis for carefully interpreting the test results. Drawing inspiration from how humans solve chess problems, we ask whether machines can possess a form of imagination. On the theoretical side, we describe how Bellman's equation may be applied to optimize the probability of winning. To conclude, we discuss the implications of our work on artificial intelligence (AI) and artificial general intelligence (AGI), suggesting possible avenues for future research.

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。

↑