Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization

Feihan Li,Yifan Sun,Weiye Zhao,Rui Chen,Tianhao Wei,Changliu Liu

提交: 2024-09-27更新: 2024-11-07

TL;DR

Safe Set Guided State-wise Constrained Policy Optimization (S-3PO) is a novel algorithm generates state-wise safe optimal policies with zero training violations.

摘要

关键词

Deep Reinforcement LearningSafe ControlSafety IndexZero Training ViolationsImaginary Cost

评审与讨论

编辑台拒稿- Submission Desk Rejected by Program Chairs

2024-11-07

直接拒稿原因

This paper is desk rejected because the authors are not anonymized.