Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs.
Bikramjit BanerjeeJeremy LyleLandon KraemerRajesh YellamrajuPublished in: AAAI (2012)
Keyphrases
- reinforcement learning
- multi agent
- distributed constraint optimization
- distributed systems
- cooperative multi agent systems
- cooperative
- peer to peer
- markov decision processes
- state space
- partially observable markov decision processes
- continuous state
- dec pomdps
- partially observable
- distributed environment
- function approximation
- policy search
- reinforcement learning algorithms
- optimal policy
- model free
- fully distributed
- distributed agents
- search algorithm
- structured peer to peer
- machine learning
- peer to peer systems
- action selection
- sample size
- learning process
- reinforcement learning methods
- markov decision problems
- average reward
- mobile agents
- dynamic programming
- multi agent systems
- learning algorithm