Mastering the Game of Sungka from Random Play

TL;DR

This paper demonstrates that a DQN agent trained with purely random play can quickly learn to master Sungka, outperforming various baselines and highlighting the effectiveness of random play in reinforcement learning.

Contribution

It introduces a stable and fast convergence training method for Sungka using random play, showing competitive performance without complex optimization.

Findings

Fast convergence of the DQN agent

Stable training process with random play

Agent consistently outperforms baseline strategies

Abstract

Recent work in reinforcement learning demonstrated that learning solely through self-play is not only possible, but could also result in novel strategies that humans never would have thought of. However, optimization methods cast as a game between two players require careful tuning to prevent suboptimal results. Hence, we look at random play as an alternative method. In this paper, we train a DQN agent to play Sungka, a two-player turn-based board game wherein the players compete to obtain more stones than the other. We show that even with purely random play, our training algorithm converges very fast and is stable. Moreover, we test our trained agent against several baselines and show its ability to consistently win against these.