AI RESEARCH
Finite-Time Analysis of MCTS in Continuous POMDP Planning
arXiv CS.AI
•
ArXi:2605.07703v1 Announce Type: new This paper presents a finite-time analysis for Monte Carlo Tree Search (MCTS) in Partially Observable Marko Decision Processes (POMDPs), with probabilistic concentration bounds in both discrete and continuous observation spaces. While MCTS-style solvers such as POMCP achieve empirical success in many applications, rigorous finite-time guarantees remain an open problem due to the nonstationarity and the interdependencies induced by heuristic action selection (e.g.