Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) is a decision-making algorithm that builds a search tree by simulating possible future outcomes, balancing exploration and exploitation to find optimal actions. Current research focuses on enhancing MCTS's efficiency and applicability in diverse domains, including quantum computing, mathematical reasoning, and autonomous agent control, often integrating it with large language models and reinforcement learning. These advancements are significantly impacting fields like AI planning, game playing, and robotics by enabling more efficient and effective decision-making in complex, uncertain environments.
Papers
Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems
Yifan Xia, Xianliang Yang, Zichuan Liu, Zhihao Liu, Lei Song, Jiang Bian
Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction
Yunhyeok Kwak, Inwoo Hwang, Dooyoung Kim, Sanghack Lee, Byoung-Tak Zhang