Learning Environment to Develop a Community of Players for Unknown Board Game

Abstract

In board games such as ancient shogi, where strategy and tactics are not well understood, a community for studying strategy and tactics is needed to train players. By machine learning how a human learner behaves in a given situation, we can build an imitation learning agent that behaves like a human. Furthermore, by using XAI technology to visualize how the imitation learning agent evaluates the board, it can be used to learn its own strategies and those of others. This learning environment can be useful for community building.