Towards Understanding Chinese Checkers with Heuristics, Monte Carlo Tree Search, and Deep Reinforcement Learning
This work addresses the problem of developing AI for Chinese Checkers, a game with unique challenges like unbounded state-space, but it is incremental as it builds on existing methods for board games.
The authors tackled the challenge of creating a competent Chinese Checkers agent by combining heuristics, Monte Carlo tree search, and deep reinforcement learning without human data, achieving performance at the level of experienced human players.
The game of Chinese Checkers is a challenging traditional board game of perfect information that differs from other traditional games in two main aspects: first, unlike Chess, all checkers remain indefinitely in the game and hence the branching factor of the search tree does not decrease as the game progresses; second, unlike Go, there are also no upper bounds on the depth of the search tree since repetitions and backward movements are allowed. Therefore, even in a restricted game instance, the state-space of the game can still be unbounded, making it challenging for a computer program to excel. In this work, we present an approach that effectively combines the use of heuristics, Monte Carlo tree search, and deep reinforcement learning for building a Chinese Checkers agent without the use of any human game-play data. Experiment results show that our agent is competent under different scenarios and reaches the level of experienced human players.