Self-Organized Cooperation Policy Setting in P2P Systems Based on Reinforcement Learning.

Golnaz Vakili Siavash Khorsandi

Published in: IEEE Syst. J. (2013)

Keyphrases

reinforcement learning
complex systems
optimal policy
machine learning
multi agent
cooperative
peer to peer
action selection
control policy
management system
computer systems
partially observable environments
markov decision process
small world
partially observable
mobile robot
digital libraries
learning algorithm