Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bejarano, Federico Pizarro, Brunke, Lukas, Schoellig, Angela P.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910753860091904
author Bejarano, Federico Pizarro
Brunke, Lukas
Schoellig, Angela P.
author_facet Bejarano, Federico Pizarro
Brunke, Lukas
Schoellig, Angela P.
contents Reinforcement learning (RL) controllers are flexible and performant but rarely guarantee safety. Safety filters impart hard safety guarantees to RL controllers while maintaining flexibility. However, safety filters can cause undesired behaviours due to the separation between the controller and the safety filter, often degrading performance and robustness. In this paper, we analyze several modifications to incorporating the safety filter in training RL controllers rather than solely applying it during evaluation. The modifications allow the RL controller to learn to account for the safety filter, improving performance. This paper presents a comprehensive analysis of training RL with safety filters, featuring simulated and real-world experiments with a Crazyflie 2.0 drone. We examine how various training modifications and hyperparameters impact performance, sample efficiency, safety, and chattering. Our findings serve as a guide for practitioners and researchers focused on safety filters and safe RL.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11671
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents
Bejarano, Federico Pizarro
Brunke, Lukas
Schoellig, Angela P.
Robotics
Machine Learning
Systems and Control
Reinforcement learning (RL) controllers are flexible and performant but rarely guarantee safety. Safety filters impart hard safety guarantees to RL controllers while maintaining flexibility. However, safety filters can cause undesired behaviours due to the separation between the controller and the safety filter, often degrading performance and robustness. In this paper, we analyze several modifications to incorporating the safety filter in training RL controllers rather than solely applying it during evaluation. The modifications allow the RL controller to learn to account for the safety filter, improving performance. This paper presents a comprehensive analysis of training RL with safety filters, featuring simulated and real-world experiments with a Crazyflie 2.0 drone. We examine how various training modifications and hyperparameters impact performance, sample efficiency, safety, and chattering. Our findings serve as a guide for practitioners and researchers focused on safety filters and safe RL.
title Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2410.11671