Optimality guarantees for particle belief approximation of POMDPs

DOI10.1613/JAIR.1.14525MaRDI QIDQ6488812

Tyler J. Becker, Mykel J. Kochenderfer, Claire J. Tomlin, Michael H. Lim, Zachary N. Sunberg

Publication date: 23 October 2023

Published in: The Journal of Artificial Intelligence Research (JAIR) (Search for Journal in Brave)

zbMATH Keywords

Markov decision processesreinforcement learningplanning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• An upper bound on the loss from approximate optimal-value functions
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• DESPOT: Online POMDP Planning with Regularization
• The Complexity of Markov Decision Processes
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
• OR Forum—A POMDP Approach to Personalize Mammography Screening Decisions
• Nonasymptotic Analysis of Monte Carlo Tree Search
• A survey of convergence results on particle filtering methods for practitioners

This page was built for publication: Optimality guarantees for particle belief approximation of POMDPs