Skill-based Safe Reinforcement Learning with Risk Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Hanping, Guo, Yuhong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913817030557696
author Zhang, Hanping
Guo, Yuhong
author_facet Zhang, Hanping
Guo, Yuhong
contents Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by exploiting auxiliary offline demonstration data. SSkP involves a two-stage process. First, we employ PU learning to learn a skill risk predictor from the offline demonstration data. Then, based on the learned skill risk predictor, we develop a novel risk planning process to enhance online safe RL and learn a risk-averse safe policy efficiently through interactions with the online RL environment, while simultaneously adapting the skill risk predictor to the environment. We conduct experiments in several benchmark robotic simulation environments. The experimental results demonstrate that the proposed approach consistently outperforms previous state-of-the-art safe RL methods.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01619
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skill-based Safe Reinforcement Learning with Risk Planning
Zhang, Hanping
Guo, Yuhong
Machine Learning
Artificial Intelligence
Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by exploiting auxiliary offline demonstration data. SSkP involves a two-stage process. First, we employ PU learning to learn a skill risk predictor from the offline demonstration data. Then, based on the learned skill risk predictor, we develop a novel risk planning process to enhance online safe RL and learn a risk-averse safe policy efficiently through interactions with the online RL environment, while simultaneously adapting the skill risk predictor to the environment. We conduct experiments in several benchmark robotic simulation environments. The experimental results demonstrate that the proposed approach consistently outperforms previous state-of-the-art safe RL methods.
title Skill-based Safe Reinforcement Learning with Risk Planning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.01619