A dynamic programming algorithm for decentralized Markov decision processes with a broadcast structure.
Jeff WuSanjay LallPublished in: CDC (2010)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- finite state
- state space
- decentralized control
- dynamic programming
- policy iteration
- transition matrices
- decision theoretic planning
- partially observable
- average cost
- action sets
- average reward
- multi agent
- planning under uncertainty
- reachability analysis
- factored mdps
- infinite horizon
- decision processes
- model based reinforcement learning
- finite horizon
- decision making
- state and action spaces
- reward function
- multiple agents