Minimax Fuzzy Q-Learning in Cooperative Multi-agent Systems.

Alper Kilic Ahmet Arslan

Published in: ADVIS (2002)

Keyphrases

multi agent reinforcement learning
cooperative multi agent systems
reinforcement learning
multi agent
fuzzy sets
fuzzy logic

cooperative
state space
function approximation
learning algorithm
membership functions
fuzzy rules

worst case
fuzzy systems
action selection
multi agent systems
optimal policy
evaluation function

fuzzy neural network
model free
learning agents
temporal difference learning
neural network