Stochastic Variance Reduction for Deep Q-learning
Machine Learning
2019-05-21 v1 Machine Learning
Abstract
Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable training and poor sample efficiency. In our paper, we proposed an innovative optimization strategy by utilizing stochastic variance reduced gradient (SVRG) techniques. With extensive experiments on Atari domain, our method outperforms the deep q-learning baselines on 18 out of 20 games.
Cite
@article{arxiv.1905.08152,
title = {Stochastic Variance Reduction for Deep Q-learning},
author = {Wei-Ye Zhao and Xi-Ya Guan and Yang Liu and Xiaoming Zhao and Jian Peng},
journal= {arXiv preprint arXiv:1905.08152},
year = {2019}
}
Comments
this is the full paper version, its extended abstract has been published