Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees

Published:2023-12-13 Issue: Volume:17 Page:8306-8311
ISSN:
Container-title:2023 62nd IEEE Conference on Decision and Control (CDC)
language:
Short-container-title:

Author:

Cao Hongpeng¹,Mao Yanbing²,Sha Lui³,Caccamo Marco⁴

Affiliation:

1. Hongpeng Cao is with School of Engineering and Design, Technical University of Munich,Munich,Germany,85748

2. Wayne State University,Yanbing Mao is with Engineering Technology Division,Detroit,MI,USA,48201

3. University of Illinois at Urbana-Champaign,Department of Computer Science,Urbana,IL,USA,61801

4. School of Engineering and Design and Institute of Robotics and Machine Intelligence, Technical University of Munich,Munich,Germany

Funder

NSF

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10383192/10383193/10383560.pdf?arnumber=10383560

Reference25 articles.

1. End-to-end training of deep visuomotor policies;Levine;The Journal of Machine Learning Research,2016

2. RMA: Rapid Motor Adaptation for Legged Robots

3. Adversarial attacks on neural network policies;Huang,2017

4. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

5. End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP