{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:15:51Z","timestamp":1784906151631,"version":"3.55.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610103","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9369-9375","source":"Crossref","is-referenced-by-count":15,"title":["Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist"],"prefix":"10.1109","author":[{"given":"Hai","family":"Nguyen","sequence":"first","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tadashi","family":"Kozuno","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian C.","family":"Beltran-Hernandez","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masashi","family":"Hamaya","sequence":"additional","affiliation":[{"name":"OMRON SINIC X Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102366"},{"key":"ref2","article-title":"Compare contact model-based control and contact model-free learning: A survey of robotic peg-in-hole assembly strategies","author":"Xu","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1980.4308347"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3224670"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160346"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AIM46323.2023.10196242"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062322-100607"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft48309.2020.9116011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197327"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341504"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aav1488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18494\/SAM.2021.3345"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3008120"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2020.0024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989292"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/app10196923"},{"key":"ref21","article-title":"Transferable force-torque dynamics model for peg-in-hole task","author":"Ding","year":"2019"},{"key":"ref22","article-title":"SO(2) equivariant reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.071"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160739"},{"key":"ref26","first-page":"3309","article-title":"Equivariant reinforcement learning under partial observability","volume-title":"Conference on Robot Learning","author":"Nguyen"},{"key":"ref27","article-title":"General E(2)-equivariant steerable cnns","volume":"32","author":"Weiler","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref29","first-page":"1640","article-title":"Belief-grounded networks for accelerated robot learning under partial observability","volume-title":"Conference on Robot Learning","author":"Nguyen"},{"key":"ref30","first-page":"1762","article-title":"Learning complementary representations of the past using auxiliary tasks in partially observable reinforcement learning","volume-title":"International Conference on Autonomous Agents and MultiAgent Systems","author":"Baisero"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1243\/PIME_PROC_1993_207_134_02"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2016.7743375"},{"key":"ref35","first-page":"16 691","article-title":"Recurrent model-free RL can be a strong baseline for many POMDPs","volume-title":"International Conference on Machine Learning","author":"Ni"},{"key":"ref36","first-page":"1673","article-title":"Leveraging fully observable policies for learning under partial observability","volume-title":"Conference on Robot Learning","author":"Nguyen"},{"key":"ref37","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref38","article-title":"Impossibly good experts and how to follow them","volume-title":"International Conference on Learning Representations","author":"Walsman"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341487"},{"key":"ref40","article-title":"The surprising effectiveness of equivariant models in domains with latent symmetry","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341471"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610103.pdf?arnumber=10610103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:14:46Z","timestamp":1723266886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610103","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}