{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:32Z","timestamp":1755993752147,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Basic Research Priorities Program of China","award":["JCKY2022110C040"],"award-info":[{"award-number":["JCKY2022110C040"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,27]]},"DOI":"10.1145\/3674746.3674762","type":"proceedings-article","created":{"date-parts":[[2024,8,21]],"date-time":"2024-08-21T18:26:08Z","timestamp":1724264768000},"page":"102-107","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reward Design for Training Robotic Insertion Tasks Using Low-Dimensional Observation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7438-062X","authenticated-orcid":false,"given":"Xinyi","family":"Li","sequence":"first","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4395-2461","authenticated-orcid":false,"given":"Huijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9837-6776","authenticated-orcid":false,"given":"Xinke","family":"Wang","sequence":"additional","affiliation":[{"name":"Automation Research Institute, China South Industries Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3557-8462","authenticated-orcid":false,"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Automation Research Institute, China South Industries Group Corporation, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623809.3623848"},{"key":"e_1_3_2_1_2_1","volume-title":"Sutton and Andrew Barto","author":"Richard","year":"2020","unstructured":"Richard S. Sutton and Andrew Barto. 2020. Reinforcement Learning: an Introduction (Second edition ed.). The MIT Press, Cambridge, Massachusetts London, England."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Conference on Robot Learning","author":"Lynch Corey","year":"2020","unstructured":"Corey Lynch, Mohi Khansari, Ted Xiao, Vikash Kumar, Jonathan Tompson, Sergey Levine, and Pierre Sermanet. 2020. Learning Latent Plans from Play. In Proceedings of the Conference on Robot Learning, May 12, 2020. PMLR, 1113\u20131132. Retrieved June 16, 2023 from https:\/\/proceedings.mlr.press\/v100\/lynch20a.html"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Henry Zhu Justin Yu Abhishek Gupta Dhruv Shah Kristian Hartikainen Avi Singh Vikash Kumar and Sergey Levine. 2020. The Ingredients of Real-World Robotic Reinforcement Learning. https:\/\/doi.org\/10.48550\/arXiv.2004.12570","DOI":"10.48550\/arXiv.2004.12570"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3188215"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95892-3_41"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211007305"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1602.01783"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3236805"}],"event":{"name":"RobCE 2024: 2024 4th International Conference on Robotics and Control Engineering","acronym":"RobCE 2024","location":"Edinburgh United Kingdom"},"container-title":["Proceedings of the 2024 4th International Conference on Robotics and Control Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674746.3674762","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674746.3674762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:47:48Z","timestamp":1755913668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674746.3674762"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":11,"alternative-id":["10.1145\/3674746.3674762","10.1145\/3674746"],"URL":"https:\/\/doi.org\/10.1145\/3674746.3674762","relation":{},"subject":[],"published":{"date-parts":[[2024,6,27]]},"assertion":[{"value":"2024-08-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}