LLM-Gomoku: A Large Language Model-Based System for Strategic Gomoku with Self-Play and Reinforcement Learning
This work addresses the problem of applying LLMs to strategic decision-making in board games like Gomoku, representing an incremental advancement in AI gaming systems.
The study tackled the challenge of using large language models (LLMs) for strategic planning in Gomoku by developing an AI system that simulates human learning, resulting in significant improvements in move selection, resolution of illegal positions, and reduced process time through parallel evaluation.
In recent years, large language models (LLMs) have shown significant advancements in natural language processing (NLP), with strong capa-bilities in generation, comprehension, and rea-soning. These models have found applications in education, intelligent decision-making, and gaming. However, effectively utilizing LLMs for strategic planning and decision-making in the game of Gomoku remains a challenge. This study aims to develop a Gomoku AI system based on LLMs, simulating the human learning process of playing chess. The system is de-signed to understand and apply Gomoku strat-egies and logic to make rational decisions. The research methods include enabling the model to "read the board," "understand the rules," "select strategies," and "evaluate positions," while en-hancing its abilities through self-play and rein-forcement learning. The results demonstrate that this approach significantly improves the se-lection of move positions, resolves the issue of generating illegal positions, and reduces pro-cess time through parallel position evaluation. After extensive self-play training, the model's Gomoku-playing capabilities have been notably enhanced.