非パラメトリック連続(PO)MDPのための行動勾配モンテカルロ木探索
Action-Gradient Monte Carlo Tree Search for Non-Parametric Continuous (PO)MDPs
連続状態・行動・観測空間でのオンライン計画に向け、木探索と勾配ベースの行動改善を組み合わせたAGMCTSを提案し、理論的保証とベンチマークでの優位性を示した。
著者: Idan Lev-Yehudi, Michael Novitsky, Moran Barenboim, Ron Benchetrit, Vadim Indelman
分類: cs.AI, cs.RO
原文アブストラクト
Online planning in continuous state, action, and observation spaces remains challenging for autonomous systems. While Monte Carlo Tree Search (MCTS) scales effectively via sampling, most continuous (PO)MDP solvers do not exploit gradient-based action optimization. We propose Action-Gradient MCTS (AGMCTS), a framework that combines global tree search with local gradient-based action refinement, while maintaining consistent value estimates. We provide three key theoretical contributions: (1) an action score gradient theorem for particle belief states; (2) the Multiple Importance Sampling (MIS) Tree that supports frequent action-branch updates by reusing prior samples without introducing estimator drift; and (3) tractable action score gradients for smooth generative models using the Area Formula. Empirical results demonstrate that AGMCTS outperforms state-of-the-art sample-based solvers in multiple challenging continuous MDP and POMDP benchmarks.
