The Complexity of Decentralized Control of Markov Decision Processes.
Daniel S. BernsteinRobert GivanNeil ImmermanShlomo ZilbersteinPublished in: Math. Oper. Res. (2002)
Keyphrases
- markov decision processes
- decentralized control
- optimal policy
- dynamic programming
- reinforcement learning
- state space
- transition matrices
- policy iteration
- decision problems
- multiagent systems
- infinite horizon
- reinforcement learning algorithms
- average cost
- partially observable
- goal oriented
- smart grid
- collective behavior
- real time dynamic programming
- grid systems
- distributed systems
- multi objective