On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP

DOI10.1287/MOOR.1070.0279MaRDI QIDQ5388068zbMATH OpenOpenAlexFDO

Authors Huizhen Yu, Dimitri P. Bertsekas

Publication date 27 May 2008

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/moor.1070.0279

zbMATH Keywords

average cost criterionfinite-state and control modelsoptimality conditionspartially observable Markov decision processes

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Control/observation systems with incomplete information (93C41) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)

Recommendations

• scientific article; zbMATH DE number 18469
• Markov control with rare state observation: average optimality
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
• On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion
• Finite-memory strategies in POMDPs with long-run average objectives

Cited in

(11)

• On the Computational Complexity of Stochastic Controller Optimization in POMDPs
• A two-state partially observable Markov decision process with three actions
• History-dependent evaluations in partially observable Markov decision process
• scientific article; zbMATH DE number 7625164 (Why is no real title available?)
• Task-guided IRL in POMDPs that scales
• POMDP controllers with optimal budget
• Reinforcement learning in non-Markovian environments
• Finite-time analysis of natural actor-critic for POMDPs
• Average cost optimality of partially observed MDPs: contraction of nonlinear filters and existence of optimal solutions and approximations
• Another look at partially observed optimal stochastic control: existence, ergodicity, and approximations without belief-reduction
• Near optimal approximations and finite memory policies for POMPDs with continuous spaces

This page was built for publication: On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5388068)