Quadratic Exponential Decrease Roll-Back: An Efficient Gradient Update Mechanism in Proximal Policy Optimization
Author:
Affiliation:
1. College of System Engineering, National University of Defense Technology,Changsha,China
2. College of Science, National University of Defense Technology,Shanghai,China
3. Shanghai Aerospace Control Technology Institude,Shanghai,China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/10339379/10339284/10339474.pdf?arnumber=10339474
Reference21 articles.
1. MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning
2. Systemic design of distributed multi-UAV cooperative decision-making for multi-target tracking
3. Coactive Design of Human-UGV Teamwork Using Augmented Reality
4. Coactive design of explainable agent-based task planning and deep reinforcement learning for human-UAVs teamwork
5. Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning
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
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3