Mastering the Game of Sungka from Random Play
This work addresses the challenge of suboptimal results in self-play reinforcement learning for game-playing agents, though it appears incremental as it applies an existing method (DQN) to a new game (Sungka) with random play.
The researchers tackled the problem of training reinforcement learning agents through self-play by exploring random play as an alternative to carefully tuned optimization methods, demonstrating that a DQN agent trained with purely random play converges quickly and stably in the game Sungka, consistently winning against several baselines.
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.