Resource-Efficient Model-Free Reinforcement Learning for Board Games

ICLR 2026 Conference Submission12682 Authors

Keywords: Reinforcement Learning, Model-Free Reinforcement Learning, Game AI, Board Games

TL;DR: We propose a simple and efficient model-free RL approach for board games that learns effectively without search.

Abstract: Board games have long served as complex decision-making benchmarks in artificial intelligence. In this field, search-based reinforcement learning methods such as AlphaZero have achieved remarkable success. However, their inherent implementation complexity and computational demands have been pointed out as barriers to their reproducibility. In this study, we propose a simple model-free reinforcement learning algorithm designed for board games to achieve more efficient learning. To validate the efficiency of the proposed method, we conducted comprehensive experiments on five board games: Animal Shogi, Gardner Chess, Go, Hex, and Othello. The results demonstrate that the proposed method achieves more efficient learning than existing methods across these environments. In addition, our extensive ablation study shows the importance of core techniques used in the proposed method. We believe that our simple yet efficient algorithm shows the potential of model-free reinforcement learning in domains traditionally dominated by search-based methods.

Primary Area: reinforcement learning

Submission Number: 12682