Partially observable Markov decision processes with imprecise parameters

DOI10.1016/j.artint.2007.03.004zbMath1168.68578OpenAlexW1995856582MaRDI QIDQ1028935

Kiyohiko Nakamura, Hideaki Itoh

Publication date: 9 July 2009

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

Full work available at URL: https://doi.org/10.1016/j.artint.2007.03.004

zbMATH Keywords

second-order beliefsPOMDPparameter setprobability interval

Mathematics Subject Classification ID

Reasoning under uncertainty in the context of artificial intelligence (68T37) Markov and semi-Markov decision processes (90C40)

Related Items

Ambiguous partially observable Markov decision processes: structural results and applications ⋮ BOUNDED-PARAMETER PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES: FRAMEWORK AND ALGORITHM ⋮ Coefficients of ergodicity for Markov chains with uncertain parameters ⋮ Policy iteration for bounded-parameter POMDPs ⋮ Sequential decision making with partially ordered preferences ⋮ A survey of decision making and optimization under uncertainty ⋮ Discrete time Markov chains with interval probabilities ⋮ Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs ⋮ An Evidential Measure of Risk in Evidential Markov Chains ⋮ IMPRECISE MARKOV CHAINS AND THEIR LIMIT BEHAVIOR

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• A new polynomial-time algorithm for linear programming
• Credal networks
• Bounded-parameter Markov decision processes
• Generalizing Markov decision processes to imprecise probabilities
• Optimal control of Markov processes with incomplete state information
• A survey of algorithmic methods for partially observed Markov decision processes
• Two perspectives on consensus for (Bayesian) inference and decisions
• Parameter Imprecision in Finite State, Finite Action Dynamic Programs
• The Complexity of Markov Decision Processes
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Markov Decision Processes with Imprecise Transition Probabilities
• Markovian Decision Processes with Uncertain Transition Probabilities
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices