Implementing ReGreT in a Decentralized Multi-agent Environment.

Stefan König Sven Kaffille Guido Wirtz

Published in: MATES (2007)

Keyphrases

multi agent environment
multi agent
multi agent systems
cooperative
single agent
online learning
expert advice
loss function
confidence bounds
worst case
lower bound
distributed systems
game theory
reinforcement learning
peer to peer
shortest path