Salvato in:
Dettagli Bibliografici
Autori principali: Li, Lingfeng, Lu, Yunlong, Wang, Yongyi, Zheng, Qifan, Li, Wenxin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.14246
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914264306941952
author Li, Lingfeng
Lu, Yunlong
Wang, Yongyi
Zheng, Qifan
Li, Wenxin
author_facet Li, Lingfeng
Lu, Yunlong
Wang, Yongyi
Zheng, Qifan
Li, Wenxin
contents People need to internalize the skills of AI agents to improve their own capabilities. Our paper focuses on Mahjong, a multiplayer game involving imperfect information and requiring effective long-term decision-making amidst randomness and hidden information. Through the efforts of AI researchers, several impressive Mahjong AI agents have already achieved performance levels comparable to those of professional human players; however, these agents are often treated as black boxes from which few insights can be gleaned. This paper introduces Mxplainer, a parameterized search algorithm that can be converted into an equivalent neural network to learn the parameters of black-box agents. Experiments on both human and AI agents demonstrate that Mxplainer achieves a top-three action prediction accuracy of over 92% and 90%, respectively, while providing faithful and interpretable approximations that outperform decision-tree methods (34.8% top-three accuracy). This enables Mxplainer to deliver both strategy-level insights into agent characteristics and actionable, step-by-step explanations for individual decisions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14246
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mxplainer: Explain and Learn Insights by Imitating Mahjong Agents
Li, Lingfeng
Lu, Yunlong
Wang, Yongyi
Zheng, Qifan
Li, Wenxin
Artificial Intelligence
People need to internalize the skills of AI agents to improve their own capabilities. Our paper focuses on Mahjong, a multiplayer game involving imperfect information and requiring effective long-term decision-making amidst randomness and hidden information. Through the efforts of AI researchers, several impressive Mahjong AI agents have already achieved performance levels comparable to those of professional human players; however, these agents are often treated as black boxes from which few insights can be gleaned. This paper introduces Mxplainer, a parameterized search algorithm that can be converted into an equivalent neural network to learn the parameters of black-box agents. Experiments on both human and AI agents demonstrate that Mxplainer achieves a top-three action prediction accuracy of over 92% and 90%, respectively, while providing faithful and interpretable approximations that outperform decision-tree methods (34.8% top-three accuracy). This enables Mxplainer to deliver both strategy-level insights into agent characteristics and actionable, step-by-step explanations for individual decisions.
title Mxplainer: Explain and Learn Insights by Imitating Mahjong Agents
topic Artificial Intelligence
url https://arxiv.org/abs/2506.14246