Deterministic policies based on maximum regrets in MDPs with imprecise rewards

DOI10.3233/AIC-190632zbMath1487.68205OpenAlexW3201191077WikidataQ113417297 ScholiaQ113417297MaRDI QIDQ5069649

Aomar Osmani, Emiliano Traversi, Pegah Alizadeh

Publication date: 19 April 2022

Published in: AI Communications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3233/aic-190632

zbMATH Keywords

branch-and-boundminimax regretMarkov decision processdeterministic policystochastic policyunknown rewards

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Cites Work

• Unnamed Item
• Unnamed Item
• Machine learning and knowledge discovery in databases. European conference, ECML PKDD 2011, Athens, Greece, September 5--9, 2011. Proceedings, Part I
• Partitioning procedures for solving mixed-variables programming problems
• Bounded-parameter Markov decision processes
• Preference-based reinforcement learning: a formal framework and a policy iteration algorithm
• Bias and Variance Approximation in Value Function Estimates
• Regret in Decision Making under Uncertainty
• Robust Markov Decision Processes
• Sampling Based Approaches for Minimizing Regret in Uncertain Markov Decision Processes (MDPs)
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Robust Dynamic Programming

This page was built for publication: Deterministic policies based on maximum regrets in MDPs with imprecise rewards