Coordination of cooperation policies in a peer-to-peer system using swarm-based RL.
Golnaz VakiliSiavash KhorsandiPublished in: J. Netw. Comput. Appl. (2012)
Keyphrases
- peer to peer
- cooperative
- multi agent
- optimal policy
- multiagent reinforcement learning
- reinforcement learning
- distributed problem solving
- multi agent systems
- decentralized control
- multiagent systems
- information sharing
- virtual enterprise
- markov decision processes
- information exchange
- markov decision process
- multi agent reinforcement learning
- resource discovery
- digital libraries
- control policies
- data sharing
- swarm intelligence
- peer to peer systems
- control policy
- peer to peer networks
- hierarchical reinforcement learning
- state space
- file sharing
- reinforcement learning algorithms
- policy search
- overlay network
- partially observable markov decision processes
- interaction protocols
- model free
- management policies
- reinforcement learning agents
- dynamic programming
- multiple agents
- cooperating agents
- distributed computing
- function approximation
- particle swarm optimization
- autonomous learning
- win win
- evolutionary algorithm
- distributed systems
- markov decision problems
- agent interactions
- action space
- reward function
- genetic algorithm
- average cost