Policy Iteration for Decentralized Control of Markov Decision Processes.
Daniel S. BernsteinChristopher AmatoEric A. HansenShlomo ZilbersteinPublished in: CoRR (2014)
Keyphrases
- markov decision processes
- decentralized control
- policy iteration
- optimal policy
- state space
- finite state
- average reward
- reinforcement learning
- transition matrices
- factored mdps
- policy evaluation
- dynamic programming
- infinite horizon
- markov decision problems
- reinforcement learning algorithms
- state and action spaces
- discounted reward
- markov decision process
- average cost
- markov games
- policy iteration algorithm
- partially observable
- search algorithm
- cooperative