Deep reinforcement learning with robust and smooth policy

Qianli Shen, Yan Li, Haoming Jiang, Zhaoran Wang, Tuo Zhao*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Scopus citations

Abstract

Deep reinforcement learning (RL) has achieved great empirical successes in various domains. However, the large search space of neural networks requires a large amount of data, which makes the current RL algorithms not sample efficient. Motivated by the fact that many environments with continuous state space have smooth transitions, we propose to learn a smooth policy that behaves smoothly with respect to states. We develop a new framework-Smooth Regularized Reinforcement Learning (SR2L), where the policy is trained with smoothness-inducing regularization. Such regularization effectively constrains the search space, and enforces smoothness in the learned policy. Moreover, our proposed framework can also improve the robustness of policy against measurement error in the state space, and can be naturally extended to distribubutionally robust setting. We apply the proposed framework to both on-policy (TRPO) and off-policy algorithm (DDPG). Through extensive experiments, we demonstrate that our method achieves improved sample efficiency and robustness.

Original languageEnglish (US)
Title of host publication37th International Conference on Machine Learning, ICML 2020
EditorsHal Daume, Aarti Singh
PublisherInternational Machine Learning Society (IMLS)
Pages8666-8677
Number of pages12
ISBN (Electronic)9781713821120
StatePublished - 2020
Event37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
Duration: Jul 13 2020Jul 18 2020

Publication series

Name37th International Conference on Machine Learning, ICML 2020
VolumePartF168147-12

Conference

Conference37th International Conference on Machine Learning, ICML 2020
CityVirtual, Online
Period7/13/207/18/20

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Human-Computer Interaction
  • Software

Fingerprint

Dive into the research topics of 'Deep reinforcement learning with robust and smooth policy'. Together they form a unique fingerprint.

Cite this