Future memories are not needed for large classes of POMDPs

DOI10.1016/j.orl.2023.02.011zbMath1525.90424arXiv2205.02580MaRDI QIDQ6106534

Axel Parmentier, Victor Cohen

Publication date: 3 July 2023

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2205.02580

zbMATH Keywords

mathematical programmingpartially observable Markov decision processdeterministic policies

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (1)

Optimal decisions in stochastic graphs with uncorrelated and correlated edge weights

Cites Work

• Finding optimal memoryless policies of POMDPs under the expected average reward criterion
• Dynamic programming and suboptimal control: a survey from ADP to MPC
• Decomposable Markov Decision Processes: A Fluid Optimization Approach
• Julia: A Fresh Approach to Numerical Computing
• The Complexity of Markov Decision Processes
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• Computability of global solutions to factorable nonconvex programs: Part I — Convex underestimating problems
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
• JuMP: A Modeling Language for Mathematical Optimization
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Future memories are not needed for large classes of POMDPs