arXiv cs.AI· Abhijeet Krishnan, Chris Martens·· 10 天前AI 评分18
面向可解释国际象棋战术的自动合成研究
Towards the Automatic Synthesis of Interpretable Chess Tactics
AI 导读
研究者提出一种符号化子策略模型，借助归纳逻辑编程系统 PAL 学习到的模式来合成可解释的国际象棋战术，并引入散度指标对照随机基线进行评估，所得战术能给出与国际象棋初学者棋力相近的走法建议。该工作还提出通过将模型接入现成引擎来进行计算评估的方案。
正文 · 原文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Symbolic Computation (cs.SC) |
| Cite as: | arXiv:2610.07640 [cs.AI] |
| (or arXiv:2610.07640v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07640 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the Explainable Agency in Artificial Intelligence Workshop, 36th AAAI Conference on Artificial Intelligence, 91-97, Mar 2022 |
Submission history
From: Abhijeet Krishnan [view email]
[v1]
Tue, 6 Oct 2026 02:35:09 UTC (41 KB)
来源：arXiv cs.AI · arxiv.org