Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search

TL;DR

This paper develops a Deep Reinforcement Learning system for Xiangqi that combines neural networks with Monte Carlo Tree Search to improve strategic gameplay and self-learning in this complex Chinese Chess variant.

Contribution

It introduces a novel DRL-MCTS framework tailored for Xiangqi, addressing its unique rules and high complexity, advancing AI in culturally significant strategy games.

Findings

Achieved strategic self-play through neural network-guided MCTS

Improved decision-making accuracy in Xiangqi

Demonstrated adaptability of DRL-MCTS to complex rule systems

Abstract

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.