Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search
By: Berk Yilmaz, Junyu Hu, Jinsong Liu
Potential Business Impact:
Makes computers play Chinese chess better.
This paper presents a Deep Reinforcement Learning (DRL) system for Xiangqi (Chinese Chess) that integrates neural networks with Monte Carlo Tree Search (MCTS) to enable strategic self-play and self-improvement. Addressing the underexplored complexity of Xiangqi, including its unique board layout, piece movement constraints, and victory conditions, our approach combines policy-value networks with MCTS to simulate move consequences and refine decision-making. By overcoming challenges such as Xiangqi's high branching factor and asymmetrical piece dynamics, our work advances AI capabilities in culturally significant strategy games while providing insights for adapting DRL-MCTS frameworks to domain-specific rule systems.
Similar Papers
Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning
Artificial Intelligence
Teaches computers to play Chinese Chess better.
Doubly Robust Monte Carlo Tree Search
Machine Learning (Stat)
Helps computers learn faster to win games.
Monte Carlo Planning with Large Language Model for Text-Based Game Agents
Computation and Language
Helps game AI learn faster by remembering past games.