Feasibility Consistent Representation Learning for Safe Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cen, Zhepeng, Yao, Yihang, Liu, Zuxin, Zhao, Ding
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914833375428608
author Cen, Zhepeng
Yao, Yihang
Liu, Zuxin
Zhao, Ding
author_facet Cen, Zhepeng
Yao, Yihang
Liu, Zuxin
Zhao, Ding
contents In the field of safe reinforcement learning (RL), finding a balance between satisfying safety constraints and optimizing reward performance presents a significant challenge. A key obstacle in this endeavor is the estimation of safety constraints, which is typically more difficult than estimating a reward metric due to the sparse nature of the constraint signals. To address this issue, we introduce a novel framework named Feasibility Consistent Safe Reinforcement Learning (FCSRL). This framework combines representation learning with feasibility-oriented objectives to identify and extract safety-related information from the raw state for safe RL. Leveraging self-supervised learning techniques and a more learnable safety metric, our approach enhances the policy learning and constraint estimation. Empirical evaluations across a range of vector-state and image-based tasks demonstrate that our method is capable of learning a better safety-aware embedding and achieving superior performance than previous representation learning baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11718
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Feasibility Consistent Representation Learning for Safe Reinforcement Learning
Cen, Zhepeng
Yao, Yihang
Liu, Zuxin
Zhao, Ding
Machine Learning
In the field of safe reinforcement learning (RL), finding a balance between satisfying safety constraints and optimizing reward performance presents a significant challenge. A key obstacle in this endeavor is the estimation of safety constraints, which is typically more difficult than estimating a reward metric due to the sparse nature of the constraint signals. To address this issue, we introduce a novel framework named Feasibility Consistent Safe Reinforcement Learning (FCSRL). This framework combines representation learning with feasibility-oriented objectives to identify and extract safety-related information from the raw state for safe RL. Leveraging self-supervised learning techniques and a more learnable safety metric, our approach enhances the policy learning and constraint estimation. Empirical evaluations across a range of vector-state and image-based tasks demonstrate that our method is capable of learning a better safety-aware embedding and achieving superior performance than previous representation learning baselines.
title Feasibility Consistent Representation Learning for Safe Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2405.11718