Decentralized control of partially observable Markov decision processes.
Christopher AmatoGirish ChowdharyAlborz GeramifardN. Kemal UreMykel J. KochenderferPublished in: CDC (2013)
Keyphrases
- partially observable markov decision processes
- decentralized control
- markov decision processes
- finite state
- reinforcement learning
- optimal policy
- multiagent systems
- state space
- partially observable
- decision problems
- dynamic programming
- collective behavior
- smart grid
- goal oriented
- infinite horizon
- multi agent
- belief state
- multi agent systems
- dynamical systems
- reinforcement learning algorithms
- markov chain
- virtual communities
- power system
- planning problems
- search space
- decision makers
- search algorithm
- grid systems
- modular robots