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

arXiv: https://arxiv.org/abs/2605.24139 · HTML: https://mlsanity.com/paper/2605.24139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 7 of 7)

- [Population Based Training of Neural Networks](https://mlsanity.com/paper/1711.09846/) (2017)
- [A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning](https://mlsanity.com/paper/1711.00832/) (2017)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games](https://mlsanity.com/paper/2310.11305/) (2023)
- [Accelerating and Improving AlphaZero Using Population Based Training](https://mlsanity.com/paper/2003.06212/) (2020)
- [Combining Prediction of Human Decisions with ISMCTS in Imperfect Information Games](https://mlsanity.com/paper/1709.09451/) (2017)
- [Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chess](https://mlsanity.com/paper/2407.05864/) (2024)

## Abstract (arXiv)

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.