Sampling Based Approaches for Minimizing Regret in Uncertain Markov Decision Processes (MDPs)

DOI10.1613/jair.5242zbMath1425.90127OpenAlexW2725263144WikidataQ129488927 ScholiaQ129488927MaRDI QIDQ5278046

Pradeep Varakantham, Yossiri Adulyasak, Asrar Ahmed, Patrick Jaillet, Meghna Lowalekar

Publication date: 13 July 2017

Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1613/jair.5242

zbMATH Keywords

minimax regretmaximin policiestransition and reward functions

Mathematics Subject Classification ID

Integer programming (90C10) Minimax problems in mathematical programming (90C47) Markov and semi-Markov decision processes (90C40)

Related Items (4)

Scenario-Based Verification of Uncertain MDPs ⋮ Deterministic policies based on maximum regrets in MDPs with imprecise rewards ⋮ An iterative security game for computing robust and adaptive network flows ⋮ A survey of decision making and optimization under uncertainty

This page was built for publication: Sampling Based Approaches for Minimizing Regret in Uncertain Markov Decision Processes (MDPs)