History-dependent evaluations in partially observable Markov decision process

DOI10.1137/20M1332876MaRDI QIDQ4990323zbMATH OpenFDO

Authors Xavier Venel, Bruno Ziliotto

Publication date 28 May 2021

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/20M1332876

zbMATH Keywords

long-run average payoffMarkov decision processpartial observation

Mathematics Subject Classification ID

Dynamical systems and their relations with probability theory and stochastic processes (37A50) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)

Recommendations

• Finite-memory strategies in POMDPs with long-run average objectives
• A survey of solution techniques for the partially observed Markov decision process
• Solution Procedures for Partially Observed Markov Decision Processes
• scientific article; zbMATH DE number 1361472
• scientific article; zbMATH DE number 14315

Cites work

• A convex analytic approach to Markov decision processes
• Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
• Blackwell optimality in Markov decision processes with partial observation.
• Discrete Dynamic Programming
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
• Discrete-Time Markovian Decision Processes with Incomplete State Observation
• scientific article; zbMATH DE number 3128733 (Why is no real title available?)
• scientific article; zbMATH DE number 3128787 (Why is no real title available?)
• scientific article; zbMATH DE number 192938 (Why is no real title available?)
• Incomplete information in Markovian decision models
• Long-term values in Markov decision processes and repeated games, and a new distance for probability spaces
• On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
• Optimal control of Markov processes with incomplete state information
• Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
• Repeated games with public uncertain duration process
• Strong uniform value in gambling houses and partially observable Markov decision processes
• Uniform value in dynamic programming

Cited in

(1)

• Establishment of history dependent decision models and construction of corresponding processes

This page was built for publication: History-dependent evaluations in partially observable Markov decision process

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4990323)