Policy iteration for bounded-parameter POMDPs

DOI10.1007/S00500-012-0932-3MaRDI QIDQ1955470zbMATH OpenOpenAlexFDO

Authors Yaodong Ni, Zhiqiang Liu

Publication date 11 June 2013

Published in Soft Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s00500-012-0932-3

zbMATH Keywords

\(\epsilon\)-optimal policybounded-parameter POMDPdecision making under uncertaintyfinite-state controlleroptimistic optimalitypolicy iteration

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Bounded-parameter partially observable Markov decision processes: framework and algorithm
• Bounded-parameter Markov decision processes
• Bounded Parameter Markov Decision Processes with Average Reward Criterion
• Partially observable Markov decision processes with imprecise parameters
• scientific article; zbMATH DE number 857623

Cites work

• Anytime point-based approximations for large POMDPS
• Bayesian Sequential Detection With Phase-Distributed Change Time and Nonlinear Penalty—A POMDP Lattice Programming Approach
• Bounded Parameter Markov Decision Processes with Average Reward Criterion
• Bounded-parameter Markov decision processes
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• Markovian Decision Processes with Uncertain Transition Probabilities
• Partially observable Markov decision processes with imprecise parameters
• Planning and acting in partially observable stochastic domains

Cited in

(14)

• Partially observable Markov decision processes with imprecise parameters
• Truncated policy iteration methods
• Reduced complexity dynamic programming based on policy iteration
• Robust topological policy iteration for infinite horizon bounded Markov decision processes
• Policy iteration type algorithms for recurrent state Markov decision processes
• Interval iteration algorithm for MDPs and IMDPs
• Policy iterations for reinforcement learning problems in continuous time and space -- fundamental theory and methods
• Bounded-parameter partially observable Markov decision processes: framework and algorithm
• Finding optimal memoryless policies of POMDPs under the expected average reward criterion
• Integrating Policy Iterations in Abstract Interpreters
• Policy iteration for robust nonstationary Markov decision processes
• Bounded Parameter Markov Decision Processes with Average Reward Criterion
• POMDP controllers with optimal budget
• Optimality guarantees for particle belief approximation of POMDPs

This page was built for publication: Policy iteration for bounded-parameter POMDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1955470)