Exploring Adaptive MCTS with TD Learning in miniXCOM
Not on the map. Why?
Abstract (arXiv)
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, we explore on-line adaptivity in MCTS without requiring pre-training. We present MCTS-TD, an adaptive MCTS algorithm improved with temporal difference learning. We 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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 25 references that are in the map. First posted on arXiv 10 Oct 2022.
Builds on
6 of 25 references.
References · 6
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2021Monte Carlo Tree Search: A Review of Recent Modifications and Applicationscited by 161
- 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
- 2021Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Modelcited by 9
- 2018Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learningcited by 8
- 2019Action Guidance with MCTS for Deep Reinforcement Learningcited by 8
Built on by
Not cited yet.