Weighted Double Q-learning.

Zongzhang Zhang Zhiyuan Pan Mykel J. Kochenderfer

Published in: IJCAI (2017)

Keyphrases

reinforcement learning
cooperative
function approximation
learning algorithm
state space
multi agent
optimal policy
weighted distance
reinforcement learning algorithms
least squares
markov chain
dynamic programming
search space
expert systems
policy iteration
multiagent learning
decision making