@inproceedings{7993ace9306140db8b68d5535a011d41,
title = "Stochastic variance reduction for deep Q-iearning",
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.",
keywords = "Deep q-learning, Gradient variance, Stochastic variance reduction",
author = "Zhao, {Wei Ye} and Jian Peng",
year = "2019",
language = "English (US)",
series = "Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",
pages = "2318--2320",
booktitle = "18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019",
note = "18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 ; Conference date: 13-05-2019 Through 17-05-2019",
}