Exploiting symmetries for single- and multi-agent partially observable stochastic domains

DOI10.1016/j.artint.2012.01.003zbMath1355.91030OpenAlexW2086556430MaRDI QIDQ456732

Byung Kon Kang, Kee-Eung Kim

Publication date: 16 October 2012

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

Full work available at URL: https://doi.org/10.1016/j.artint.2012.01.003

zbMATH Keywords

symmetryPOMDPgraph automorphismPOSG

Mathematics Subject Classification ID

Programming involving graphs or networks (90C35) Decision theory (91B06)

Uses Software

• nauty

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• A survey of solution techniques for the partially observed Markov decision process
• On the undecidability of probabilistic planning and related stochastic optimization problems
• Equivalence notions and model minimization in Markov decision processes
• Algorithms for highly symmetric linear and integer programs
• The Complexity of Markov Decision Processes
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Algorithmic Game Theory
• The Complexity of Decentralized Control of Markov Decision Processes