Abstract We show that Deep Neural Networks introduce two heteroscedastic Gumbel noise
sources into Q-Learning. To account for these noise sources, we propose Double Gumbel Q …

Collective cooperation is essential for the survival and advancement of groups. However,
current studies on evolutionary dynamics within higher-order networks often focus on …

It is a longstanding problem that Q-learning suffers from the overestimation bias. This issue
originates from the fact that Q-learning uses the expectation of maximum Q-value to …

We study whether the learning rate $\alpha $, the discount factor $\gamma $ and the reward
signal $ r $ have an influence on the overestimation bias of the Q-Learning algorithm. Our …

Deep Reinforcement Learning has produced decision makers that play Chess, Go, Shogi,
Atari, and Starcraft with superhuman ability. However, unlike animals and humans, these …

This paper revisits the estimation bias control problem of Q-learning, motivated by the fact
that the estimation bias is not always evil, ie, some environments benefit from overestimation …