Optimally solving Dec-POMDPs as continuous-state MDPs

DOI10.1613/JAIR.4623MaRDI QIDQ2790147zbMATH OpenOpenAlexFDO

Authors Jilles Steeve Dibangoye, Christopher Amato, Olivier Buffet, François Charpillet

Publication date 3 March 2016

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

Full work available at URL https://doi.org/10.1613/jair.4623

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Agent technology and artificial intelligence (68T42) Markov and semi-Markov decision processes (90C40)

Recommendations

• Incremental clustering and expansion for faster optimal planning in decentralized POMDPs
• scientific article; zbMATH DE number 5547972
• Modeling and Planning with Macro-Actions in Decentralized POMDPs
• Optimal and approximate Q-value functions for decentralized POMDPS
• An investigation into mathematical programming for finite horizon decentralized POMDPS

Cited in

(29)

• A decentralized partially observable decision model for recognizing the multiagent goal in simulation systems
• Multi-agent reinforcement learning algorithm to solve a partially-observable multi-agent problem in disaster response
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• Knowledge-based strategies for multi-agent teams playing against nature
• A decentralized partially observable Markov decision model with action duration for goal recognition in real time strategy games
• Rethinking formal models of partially observable multiagent decision making
• Value functions for depth-limited solving in zero-sum imperfect-information games
• Multiagent expedition with graphical models
• Probabilistic inference techniques for scalable multiagent decision making
• A concise introduction to decentralized POMDPs
• A hybrid continuous max-sum algorithm for decentralised coordination
• Sample-based policy iteration for constrained DEC-POMDPs
• An investigation into mathematical programming for finite horizon decentralized POMDPS
• Parallel Markov decision processes
• The cross-entropy method for policy search in decentralized POMDPs
• Communication-based decomposition mechanisms for decentralized MDPS
• Optimal and approximate Q-value functions for decentralized POMDPS
• Centralized Optimization for Dec-POMDPs Under the Expected Average Reward Criterion
• Exploiting symmetries for single- and multi-agent partially observable stochastic domains
• Incremental clustering and expansion for faster optimal planning in decentralized POMDPs
• scientific article; zbMATH DE number 7625165 (Why is no real title available?)
• Scalable Online Planning for Multi-Agent MDPs
• Decision-theoretic planning under anonymity in agent populations
• scientific article; zbMATH DE number 2243376 (Why is no real title available?)
• scientific article; zbMATH DE number 2243386 (Why is no real title available?)
• Decentralized Incremental Fuzzy Reinforcement Learning for Multi-Agent Systems
• Solving zero-sum one-sided partially observable stochastic games
• HSVI can solve zero-sum partially observable stochastic games
• An oracle-guided approach to constrained policy synthesis under uncertainty

This page was built for publication: Optimally solving Dec-POMDPs as continuous-state MDPs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2790147)