发表机构
North Carolina State University（北卡罗来纳州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该工作提出一种基于归纳逻辑编程的符号子策略模型，用于生成可解释的国际象棋战术，并通过散度度量与引擎增强评估其有效性。
AI 中文摘要
最先进的强化学习智能体能够在国际象棋、围棋和星际争霸II等游戏中超越人类专家。这些智能体不仅利用数字硬件在反应和计算速度上快于人类，还采用了更优的策略从而获得更多胜利。解读这些策略将为人类棋手提供宝贵的见解，帮助他们改进棋艺。在这项初步工作中，我们提出了一种用于下国际象棋的符号子策略模型。受国际象棋战术的启发，我们的模型尝试融入领域知识以提高可解释性。我们调整了由归纳逻辑编程系统PAL学到的模式来推导我们的模型。我们提出了一种散度度量，用于将我们的模型与随机基线进行评估对比，并找到一组战术，其建议的走法强度与人类初学者相当。最后，我们通过将现成的引擎与模型增强，提出了一种针对该模型的计算评估方案。
英文摘要
State-of-the-art reinforcement learning agents are capable of outperforming human experts at games like chess, Go and StarCraft II. These agents do not simply take advantage of their digital hardware in being able to react and calculate faster than humans, but employ better strategies that lead to more victories. Interpreting these strategies would give human players valuable insight into how to improve their play. In this preliminary work, we propose a symbolic sub-policy model for playing chess. Inspired by chess tactics, our model attempts to incorporate domain knowledge to improve interpretability. We adapt patterns learned by an inductive logic programming system called PAL to derive our model. We contribute a divergence metric to evaluate our model against a random baseline, and find a set of tactics that is able to suggest moves of similar playing strength to a human beginner. Finally, we propose a computational evaluation scheme for the model by augmenting an off-the-shelf engine with it.
Journal refProceedings of the Explainable Agency in Artificial Intelligence Workshop, 36th AAAI Conference on Artificial Intelligence, 91-97, Mar 2022
