{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:25Z","timestamp":1759331845607,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,20]],"date-time":"2022-08-20T00:00:00Z","timestamp":1660953600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,20]],"date-time":"2022-08-20T00:00:00Z","timestamp":1660953600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,20]]},"DOI":"10.1109\/case49997.2022.9926540","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:58:44Z","timestamp":1667523524000},"page":"1405-1410","source":"Crossref","is-referenced-by-count":5,"title":["Expert Initialized Reinforcement Learning with Application to Robotic Assembly"],"prefix":"10.1109","author":[{"given":"Jeppe","family":"Langaa","sequence":"first","affiliation":[{"name":"University of Southern Denmark,Maersk McKinney Moller Institute,Odense,Denmark"}]},{"given":"Christoffer","family":"Sloth","sequence":"additional","affiliation":[{"name":"University of Southern Denmark,Maersk McKinney Moller Institute,Odense,Denmark"}]}],"member":"263","reference":[{"article-title":"Solving rubiks cube with a robot hand","year":"2019","author":"AI","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"article-title":"Openai five","year":"2018","author":"AI","key":"ref3"},{"article-title":"Learning dexterous in-hand manipulation","year":"2019","author":"AI","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref6","first-page":"2451","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31. Curran Associates, Inc."},{"article-title":"Auto-encoding variational bayes","year":"2014","author":"Kingma","key":"ref7"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3150225","article-title":"Multi-robot assembly strategies and metrics","volume":"51","author":"Marvel","year":"2018","journal-title":"ACM Computing Surveys"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2791591"},{"article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","year":"2020","author":"Goecks","key":"ref10"},{"key":"ref11","article-title":"Deterministic policy gradient algorithms","volume-title":"31st International Conference on Machine Learning, ICML 2014","volume":"1","author":"Silver"},{"article-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref14","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proceedings of the 12th International Conference on Neural Information Processing Systems","author":"Sutton"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1934-6093.1999.tb00003.x"},{"key":"ref19","article-title":"Mujoco documentation"},{"key":"ref20","article-title":"Iso tolerances for holes (iso 286-2)"}],"event":{"name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2022,8,20]]},"location":"Mexico City, Mexico","end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9926286\/9926419\/09926540.pdf?arnumber=9926540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T09:37:27Z","timestamp":1725442647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9926540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,20]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/case49997.2022.9926540","relation":{},"subject":[],"published":{"date-parts":[[2022,8,20]]}}}