Momentum in Reinforcement Learning
Machine Learning
2020-04-01 v2 Machine Learning
Abstract
We adapt the optimization's concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momentum as an average of consecutive -functions. We derive Momentum Value Iteration (MoVI), a variation of Value Iteration that incorporates this momentum idea. Our analysis shows that this allows MoVI to average errors over successive iterations. We show that the proposed approach can be readily extended to deep learning. Specifically, we propose a simple improvement on DQN based on MoVI, and experiment it on Atari games.
Keywords
Cite
@article{arxiv.1910.09322,
title = {Momentum in Reinforcement Learning},
author = {Nino Vieillard and Bruno Scherrer and Olivier Pietquin and Matthieu Geist},
journal= {arXiv preprint arXiv:1910.09322},
year = {2020}
}
Comments
AISTATS 2020