Safe Intermittent Reinforcement Learning with Static and Dynamic Event Generators

Author

Yongliang Yang
Kyriakos G. Vamvoudakis
Hamidreza Modares, Missouri University of Science and TechnologyFollow
Yixin Yin, University of Science and Technology Beijing
Donald C. Wunsch, Missouri University of Science and TechnologyFollow

Abstract

In this article, we present an intermittent framework for safe reinforcement learning (RL) algorithms. First, we develop a barrier function-based system transformation to impose state constraints while converting the original problem to an unconstrained optimization problem. Second, based on optimal derived policies, two types of intermittent feedback RL algorithms are presented, namely, a static and a dynamic one. We finally leverage an actor/critic structure to solve the problem online while guaranteeing optimality, stability, and safety. Simulation results show the efficacy of the proposed approach.

Recommended Citation

Y. Yang et al., "Safe Intermittent Reinforcement Learning with Static and Dynamic Event Generators," IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 12, pp. 5441 - 5455, Institute of Electrical and Electronics Engineers (IEEE), Feb 2020.

The definitive version is available at https://doi.org/10.1109/TNNLS.2020.2967871

Department(s)

Electrical and Computer Engineering

Second Department

Computer Science

Research Center/Lab(s)

Center for High Performance Computing Research

Comments

National Science Foundation, Grant S&AS-1849264

Keywords and Phrases

Actor/Critic Structures; Asymptotic Stability; Barrier Functions; Reinforcement Learning (RL); Safety-Critical Systems

International Standard Serial Number (ISSN)

2162-237X; 2162-2388

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2020 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

10 Feb 2020

PubMed ID

32054590