Adaptive Negotiation Based on Rewards and Regret in a Multi-Agent Environment.

Adina Magda Florea Eugenia Kalisz

Published in: SYNASC (2007)

Keyphrases

multi agent environment
multi agent systems
multi agent
bandit problems
reinforcement learning
single agent
cooperative
conflict resolution
lower bound
software agents
worst case
markov decision processes
game theory
online learning
loss function
autonomous agents
decision problems
e learning