Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method

This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown system dynamics and environment constraints given a significa...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-03
Main Authors: Liu, Zuxin, Zhou, Hongyi, Chen, Baiming, Zhong, Sicheng, Hebert, Martial, Zhao, Ding
Format: Article
Language:English
Subjects:
Constraint modelling
Entropy
Learning
Neural networks
Predictive control
Robustness
System dynamics
Uncertainty
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper studies the constrained/safe reinforcement learning (RL) problem with sparse indicator signals for constraint violations. We propose a model-based approach to enable RL agents to effectively explore the environment with unknown system dynamics and environment constraints given a significantly small number of violation budgets. We employ the neural network ensemble model to estimate the prediction uncertainty and use model predictive control as the basic control framework. We propose the robust cross-entropy method to optimize the control sequence considering the model uncertainty and constraints. We evaluate our methods in the Safety Gym environment. The results show that our approach learns to complete the tasks with a much smaller number of constraint violations than state-of-the-art baselines. Additionally, we are able to achieve several orders of magnitude better sample efficiency when compared with constrained model-free RL approaches. The code is available at \url{https://github.com/liuzuxin/safe-mbrl}.
ISSN:2331-8422