Alpha-Mini: Minichess Agent with Deep Reinforcement Learning

2021/12/22 by Michael Sun, Sun, Michael, Robert Tan +1
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.LG

paper · pdf · doi:10.48550/arxiv.2112.13666

arxiv created 2021/12/22 · arxiv updated 2021/12/28

Abstract

We train an agent to compete in the game of Gardner minichess, a downsized variation of chess played on a 5x5 board. We motivated and applied a SOTA actor-critic method Proximal Policy Optimization with Generalized Advantage Estimation. Our initial task centered around training the agent against a random agent. Once we obtained reasonable performance, we then adopted a version of iterative policy improvement adopted by AlphaGo to pit the agent against increasingly stronger versions of itself, and evaluate the resulting performance gain. The final agent achieves a near (.97) perfect win rate against a random agent. We also explore the effects of pretraining the network using a collection of positions obtained via self-play.

Related

• Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess
• Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
• AlphaDDA: Strategies for Adjusting the Playing Strength of a Fully Trained AlphaZero System to a Suitable Human Training Partner
• Enhancing Chess Reinforcement Learning with Graph Representation
• Minibal: Balanced Game-Playing Without Opponent Modeling