{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:58:39Z","timestamp":1772823519512,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811792","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"9867-9873","source":"Crossref","is-referenced-by-count":2,"title":["Model-driven reinforcement learning and action dimension extension method for efficient asymmetric assembly"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Gai","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Mechanical Engineering,Beijing,China"}]},{"given":"Jiuming","family":"Guo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mechanical Engineering,Beijing,China"}]},{"given":"Dan","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mechanical Engineering,Beijing,China"}]},{"given":"Ken","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Mechanical Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1115\/1.4041331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2868859"},{"key":"ref13","article-title":"Parameter Space Noise for Exploration","author":"plappert","year":"2017","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref16","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Advances in Neural Information Processing Systems 29 (NIPS)"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1995.10484354"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907370117"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2352605"},{"key":"ref3","article-title":"Feature-Based Compliance Control for Peg-in-Hole Assembly with Clearance or Interference Fit","author":"gai","year":"2021","journal-title":"ArXiv"},{"key":"ref6","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref5","article-title":"Accelerated Methods for Deep Reinforcement Learning","author":"stooke","year":"2018","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"ref7","article-title":"Emergence of Locomotion Behaviours in Rich Environments","author":"heess","year":"2017","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2838069"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1115\/1.3149634"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.088"},{"key":"ref22","article-title":"Learning Latent Representations to Influence Multi-Agent Interaction","author":"xie","year":"0","journal-title":"4th Annual Conference on Robot Learning (CoRL)"},{"key":"ref21","article-title":"Offline Meta-Reinforcement Learning for Industrial Insertion","author":"zhao","year":"2021","journal-title":"ArXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811792.pdf?arnumber=9811792","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:50Z","timestamp":1667516750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811792\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811792","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}