Optimal and approximate Q-value functions for decentralized POMDPS

MaRDI QIDQ3624133zbMATH OpenFDO

Authors Frans A. Oliehoek, Matthijs T. J. Spaan, Nikos Vlassis

Publication date 28 April 2009

Full work available at URL https://arxiv.org/abs/1111.0062

zbMATH Keywords

decision makingdecision-theoretic planning

Mathematics Subject Classification ID

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

Recommendations

• Optimally solving Dec-POMDPs as continuous-state MDPs
• scientific article; zbMATH DE number 1509479
• scientific article; zbMATH DE number 5547972
• Modeling and Planning with Macro-Actions in Decentralized POMDPs
• The cross-entropy method for policy search in decentralized POMDPs

Cited in

(14)

• A unified framework for stochastic optimization
• Multi-agent reinforcement learning algorithm to solve a partially-observable multi-agent problem in disaster response
• Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication
• A leader-follower partially observed, multiobjective Markov game
• Optimally solving Dec-POMDPs as continuous-state MDPs
• An investigation into mathematical programming for finite horizon decentralized POMDPS
• The cross-entropy method for policy search in decentralized POMDPs
• Centralized Optimization for Dec-POMDPs Under the Expected Average Reward Criterion
• Controlling a Fleet of Unmanned Aerial Vehicles to Collect Uncertain Information in a Threat Environment
• Byzantine-Resilient Decentralized Policy Evaluation With Linear Function Approximation
• Monotonic value function factorisation for deep multi-agent reinforcement learning
• Online planning for multi-agent systems with bounded communication
• A sufficient statistic for influence in structured multiagent environments
• On centralized critics in multi-agent reinforcement learning

Describes a project that uses

Uses Software

• POMDPS

This page was built for publication: Optimal and approximate Q-value functions for decentralized POMDPS

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3624133)