Distributed Reinforcement Learning via Gossip.
Adwaitvedant S. MathkarVivek S. BorkarPublished in: CoRR (2013)
Keyphrases
- reinforcement learning
- distributed systems
- distributed environment
- multi agent
- cooperative
- distributed network
- state space
- function approximation
- machine learning
- reinforcement learning algorithms
- fault tolerant
- peer to peer
- learning problems
- markov decision processes
- computer networks
- loosely coupled
- least squares
- distributed data
- social networks
- distributed learning
- reinforcement learning methods
- database