Exploring Adaptive MCTS with TD Learning in miniXCOM
In this EXAG 2022 presentation, Kimiya Saadat discusses how in recent years, Monte Carlo tree search (MCTS) has achieved widespread adoption within the game community. Its use in conjunction with deep reinforcement learning has produced success stories in many applications. While these approaches have been implemented in various games, from simple board games to more complicated video games such as StarCraft, the use of deep neural networks requires a substantial training period. In this work, they explore on-line adaptivity in MCTS without requiring pre-training. They present MCTS-TD, an adaptive MCTS algorithm improved with temporal difference learning. They demonstrate our new approach on the game miniXCOM, a simplified version of XCOM, a popular commercial franchise consisting of several turn-based tactical games, and show how adaptivity in MCTS-TD allows for improved performances against opponents.