Correlation minimizing replay memory in temporal-difference reinforcement learning

doi:10.1016/j.neucom.2020.02.004

Correlation minimizing replay memory in temporal-difference reinforcement learning

2020-06-01

12

PRE

AI

DOI：10.1016/j.neucom.2020.02.004

原文链接

原文求助

摘要

En 中文

Online reinforcement learning agents are now able to process an increasing amount of data which makes their approximation and compression into value functions a more demanding task. To improve approximation, thus the learning process itself, it has been proposed to select randomly a mini-batch of the past experiences that are stored in the replay memory buffer to be replayed at each learning step. In this work, we present an algorithm that classifies and samples the experiences into separate contextual memory buffers using an unsupervised learning technique. This allows each new experience to be associated to a mini-batch of the past experiences that are not from the same contextual buffer as the current one, thus further reducing the correlation between experiences. Experimental results show that the correlation minimizing sampling improves over Q-learning algorithms with uniform sampling, and that a significant improvement can be observed when coupled with the sampling methods that prioritize on the experience temporal difference error. (C) 2020 Elsevier B.V. All rights reserved.

Keyword:

Reinforcement learning

Temporal-difference learning

Replay memory

Artificial neural networks

Correlation minimizing replay memory in temporal-difference reinforcement learning

摘要

期刊

机构

引用论文