Finding optimal memoryless policies of POMDPs under the expected average reward criterion

DOI10.1016/J.EJOR.2010.12.014MaRDI QIDQ418072zbMATH OpenOpenAlexFDO

Authors Baoqun Yin, Yanjie Li, Hongsheng Xi

Publication date 14 May 2012

Published in European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ejor.2010.12.014

zbMATH Keywords

correlated actionsmemoryless policyperformance differencepolicy iteration with step sizesPOMDPs

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Finding Optimal Observation-Based Policies for Constrained POMDPs Under the Expected Average Reward Criterion
• Finite-memory strategies in POMDPs with long-run average objectives
• Average optimality for continuous-time Markov decision processes with a policy iteration approach
• On Finding Optimal Policies for Markov Decision Chains: A Unifying Framework for Mean-Variance-Tradeoffs
• The policy iteration algorithm for average reward Markov decision processes with general state space
• Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion
• Policy iteration for bounded-parameter POMDPs
• On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes

Cites work

• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 1753152 (Why is no real title available?)
• scientific article; zbMATH DE number 1753153 (Why is no real title available?)
• A survey of algorithmic methods for partially observed Markov decision processes
• Basic ideas for event-based optimization of Markov systems
• CONVERGENCE OF SIMULATION-BASED POLICY ITERATION
• Event-Based Optimization of Markov Systems
• Optimization of a special case of continuous-time Markov decision processes with compact action set
• Performance optimization algorithms based on potentials for semi-Markov control processes
• Perturbation realization, potentials, and sensitivity analysis of Markov processes
• Potential-Based Online Policy Iteration Algorithms for Markov Decision Processes
• Simulation-based optimization of Markov reward processes
• Stochastic learning and optimization. A sensitivity-based approach.
• The $n$th-Order Bias Optimality for Multichain Markov Decision Processes
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon

Cited in

(6)

• Mean-payoff optimization in continuous-time Markov chains with parametric alarms
• Finite-memory strategies in POMDPs with long-run average objectives
• Geometry of policy improvement
• Centralized Optimization for Dec-POMDPs Under the Expected Average Reward Criterion
• scientific article; zbMATH DE number 7625165 (Why is no real title available?)
• Future memories are not needed for large classes of POMDPs

Describes a project that uses

Uses Software

• POMDP

This page was built for publication: Finding optimal memoryless policies of POMDPs under the expected average reward criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q418072)