POMDPs under probabilistic semantics

• Published in: Artificial intelligence Vol. 221; pp. 46 - 72
• Main Authors: Chatterjee, Krishnendu, Chmelík, Martin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2015
• Subjects: Algorithms; Almost-sure winning; Artificial intelligence; Expert systems; Intervals; Limit-average objectives; Markov processes; POMDPs; Probabilistic methods; Probability theory; Semantics; Thresholds; POMDPs; Limit-average objectives; Almost-sure winning

We consider partially observable Markov decision processes (POMDPs) with limit-average payoff, where a reward value in the interval [0,1] is associated with every transition, and the payoff of an infinite path is the long-run average of the rewards. We consider two types of path constraints: (i) a q...