Sign in
Hysteretic q-learning : an algorithm for decentralized reinforcement learning in cooperative multi-agent teams.
Laëtitia Matignon
Guillaume J. Laurent
Nadine Le Fort-Piat
Published in:
IROS (2007)
Keyphrases
</>
cooperative
reinforcement learning
learning algorithm
dynamic programming
stochastic approximation
multi agent
computational complexity
model free
optimal solution
np hard
worst case
function approximation
reinforcement learning algorithms
object recognition
mathematical model