On the Estimation Bias in Double Q-Learning.

Zhizhou Ren Guangxiang Zhu Hao Hu Beining Han Jianglun Chen Chongjie Zhang

Published in: CoRR (2021)

Keyphrases

reinforcement learning
cooperative
state space
learning algorithm
multi agent
parameter estimation
function approximation
estimation algorithm
estimation error
model free
estimation accuracy
learning rate
action selection
accurate estimation