On the Reduction of Variance and Overestimation of Deep Q-Learning

arXiv:1910.05983v2 Announce Type: replace
Abstract: The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and …

abstract algorithm algorithms arxiv cs.lg design environments extensions q-learning reduce reinforcement reinforcement learning robust stat.ml type types values variance