An offline-to-online reinforcement learning approach based on multi-action evaluation with policy extension

Author:

Cheng Xuebo,Huang XiaohuiORCID,Huang Zhichao,Jiang Nan

Funder

Innovative Research Group Project of the National Natural Science Foundation of China

Natural Science Foundation of Jiangxi Province

Publisher

Springer Science and Business Media LLC

Reference40 articles.

1. Fu J, Kumar A, Nachum O, Tucker G, Levine S (2020) D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219

2. McDonald MJ, Hadfield-Menell D (2022) Guided imitation of task and motion planning. Proceedings of the 5th conference on robot learning. 164:630–640

3. Chen X, Yao L, McAuley J, Zhou G, Wang X (2023) Deep reinforcement learning in recommender systems: A survey and new perspectives. Knowl-Based Syst 264:110335

4. Sharif Razavian A, Azizpour H, Sullivan J, Carlsson S (2014) CNN features off-the-shelf: An astounding baseline for recognition. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) workshops

5. Gupta A, Kumar V, Lynch C, Levine S, Hausman K (2020) Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning. Proceedings of the Conference on Robot Learning. 100:1025–1037

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

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