Solving factored MDPs using non-homogeneous partitions

DOI10.1016/S0004-3702(02)00377-6zbMath1082.68804OpenAlexW2038694949MaRDI QIDQ814475

N. E. Zubov

Publication date: 7 February 2006

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

Full work available at URL: https://doi.org/10.1016/s0004-3702(02)00377-6

zbMATH Keywords

Factored Markov decision processesNon-homogeneous partitioning methodPlanning under uncertainty

Mathematics Subject Classification ID

Reasoning under uncertainty in the context of artificial intelligence (68T37) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items

Influence of modeling structure in probabilistic sequential decision problems

Uses Software

• CUDD

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An upper bound on the loss from approximate optimal-value functions
• Stochastic dynamic programming with factored representations
• Bounded-parameter Markov decision processes
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Technical update: Least-squares temporal difference learning
• The Complexity of Markov Decision Processes
• Adaptive aggregation methods for infinite horizon dynamic programming
• Markov Decision Processes with Imprecise Transition Probabilities