Scalable Anytime Planning for Multi-Agent MDPs.

Shushman Choudhury Jayesh K. Gupta Peter Morales Mykel J. Kochenderfer

Published in: AAMAS (2021)

Keyphrases

multi agent
planning under uncertainty
reinforcement learning
stochastic domains
markov decision processes
probabilistic planning
planning problems
sequential decision making problems
markov decision problems

single agent
multi agent systems
factored mdps
ai planning
partially observable markov decision processes
partially observable
dec pomdps
decision theoretic planning
reactive agents

state space
factored markov decision processes
decision theoretic
coalition formation
policy iteration
cooperative
multi agent planning
heuristic search
multiagent systems

team formation
intelligent agents
optimal policy
anytime algorithms
action selection
blocks world
planning process
finite horizon
planning domains