MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Qian-Rong, Guei, Hung, Wu, I-Chen, Wu, Ti-Rong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913157833818112
author Li, Qian-Rong
Guei, Hung
Wu, I-Chen
Wu, Ti-Rong
author_facet Li, Qian-Rong
Guei, Hung
Wu, I-Chen
Wu, Ti-Rong
contents Imperfect-information games (IIGs) are challenging, as players must make decisions without fully observing the true game state. While AlphaZero has achieved remarkable success in perfect-information games, extending it to IIGs remains difficult. Existing search-based approaches, such as Perfect Information Monte Carlo (PIMC), suffer from strategy fusion, while Information Set Monte Carlo Tree Search (IS-MCTS) incurs high computational cost when combined with neural networks. In this paper, we propose Multi-State Aggregated PoLicy Evaluation (MAPLE), a tree search method that aggregates policy and value evaluations from multiple sampled world states within a single search tree, combining the advantages of PIMC and IS-MCTS while maintaining a controllable computational cost. We further incorporate a Siamese-based sampling strategy to select informative world states from the information set. Experiments on Phantom Go and Dark Hex show that MAPLE significantly outperforms the PIMC-based AlphaZero baseline, achieving Elo improvements of 291 and 136, respectively. These results demonstrate that MAPLE is an effective approach for AlphaZero-style learning in imperfect-information games.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24139
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
Li, Qian-Rong
Guei, Hung
Wu, I-Chen
Wu, Ti-Rong
Artificial Intelligence
Machine Learning
Imperfect-information games (IIGs) are challenging, as players must make decisions without fully observing the true game state. While AlphaZero has achieved remarkable success in perfect-information games, extending it to IIGs remains difficult. Existing search-based approaches, such as Perfect Information Monte Carlo (PIMC), suffer from strategy fusion, while Information Set Monte Carlo Tree Search (IS-MCTS) incurs high computational cost when combined with neural networks. In this paper, we propose Multi-State Aggregated PoLicy Evaluation (MAPLE), a tree search method that aggregates policy and value evaluations from multiple sampled world states within a single search tree, combining the advantages of PIMC and IS-MCTS while maintaining a controllable computational cost. We further incorporate a Siamese-based sampling strategy to select informative world states from the information set. Experiments on Phantom Go and Dark Hex show that MAPLE significantly outperforms the PIMC-based AlphaZero baseline, achieving Elo improvements of 291 and 136, respectively. These results demonstrate that MAPLE is an effective approach for AlphaZero-style learning in imperfect-information games.
title MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.24139