.png){kind=icon}
返回
World-class interpretable poker
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-022-06179-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We address the problem of interpretability in iterative game solving for imperfect-information games such as poker. This lack of interpretability has two main sources: first, the use of an uninterpretable feature representation, and second, the use of black box methods such as neural networks, for the fitting procedure. In this paper, we present advances on both fronts. Namely, first we propose a novel, compact, and easy-to-understand game-state feature representation for Heads-up No-limit (HUNL) Poker. Second, we make use of globally optimal decision trees, paired with a counterfactual regret minimization (CFR) self-play algorithm, to train our poker bot which produces an entirely interpretable agent. Through experiments against Slumbot, the winner of the most recent Annual Computer Poker Competition, we demonstrate that our approach yields a HUNL Poker agent that is capable of beating the Slumbot. Most exciting of all, the resulting poker bot is highly interpretable, allowing humans to learn from the novel strategies it discovers.
Keyword:
Optimal decision trees
Game solving
Deep reinforcement learning
Artificial intelligence
Interpretability
Poker
Regret minimization
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
分享收藏Calibration of Discrete-Element-Method Parameters for Cohesive Materials Using Dynamic-Yield-Strength and Shear-Cell Experiments.png)
Processes
OAAI
ProcessesIF0
OAAI分享收藏分享收藏
查看更多内容