Alpha-Mini: Minichess Agent with Deep Reinforcement Learning
Machine Learning
2021-12-28 v1 Artificial Intelligence
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.
Cite
@article{arxiv.2112.13666,
title = {Alpha-Mini: Minichess Agent with Deep Reinforcement Learning},
author = {Michael Sun and Robert Tan},
journal= {arXiv preprint arXiv:2112.13666},
year = {2021}
}