Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty
Author:
Affiliation:
1. Chinese Academy of Sciences,Institute of Intelligent Machines, HFIPS,Hefei,China
2. Chinese Academy of Sciences,Institute of Plasma Physics, HFIPS,Hefei,China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9863218/9863240/09863259.pdf?arnumber=9863259
Reference26 articles.
1. Hindsight experience replay;andrychowicz;Advances in neural information processing systems,2017
2. Calibration-Free Monocular Vision-Based Robot Manipulations With Occlusion Awareness
3. Identity Mappings in Deep Residual Networks
4. Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
5. End-To-End Robotic Reinforcement Learning without Reward Engineering
Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Redirection Strategy Switching: Selective Redirection Controller for Dynamic Environment Adaptation;IEEE Transactions on Visualization and Computer Graphics;2024-05
2. Improved 1vs1 Air Combat Model With Self-Play Soft Actor-Critic and Sparse Rewards;2023 23rd International Conference on Control, Automation and Systems (ICCAS);2023-10-17
3. D2SR: Transferring Dense Reward Function to Sparse by Network Resetting;2023 IEEE International Conference on Real-time Computing and Robotics (RCAR);2023-07-17
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