{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:16:04Z","timestamp":1735276564245,"version":"3.32.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801334","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"12671-12678","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Push Manipulation by Mobile Robots"],"prefix":"10.1109","author":[{"given":"So","family":"Kuroki","sequence":"first","affiliation":[{"name":"OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan"}]},{"given":"Mai","family":"Nishimura","sequence":"additional","affiliation":[{"name":"OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan"}]},{"given":"Tadashi","family":"Kozuno","sequence":"additional","affiliation":[{"name":"OM-RON SINIC X Corporation,Bunkyo-ku, Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191170"},{"key":"ref2","first-page":"1995","article-title":"Coordinated multi-agent imitation learning","volume-title":"Proc. ICML","author":"Le"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561274"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3261751"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/robot.2002.1013392"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2400731"},{"key":"ref7","first-page":"2181","article-title":"Learning and retrieval from prior data for skill-based imitation learning","volume-title":"Proc. CoRL","author":"Nasiriany"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.011"},{"article-title":"Multi-agent manipulation via locomotion using hierarchical sim2real","volume-title":"Proc. CoRL","author":"Nachum","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561359"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref12","first-page":"459","article-title":"Plant: Explainable planning transformers via object-level representations","volume-title":"Proc. CoRL","author":"Renz"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812450"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA57147.2024.10611615","article-title":"Rh20t: A robotic dataset for learning diverse skills in one-shot","volume-title":"RSS 2023 Workshop on Learning for Task and Motion Planning","author":"Fang"},{"key":"ref15","first-page":"879","article-title":"Roboturk: A crowdsourcing platform for robotic skill learning through imitation","volume-title":"Proc. CoRL","author":"Mandlekar"},{"key":"ref16","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"CoRR"},{"key":"ref17","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Vuong","year":"2023","journal-title":"Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition@CoRL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2007-11508"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642870"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652073"},{"key":"ref24","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2020","journal-title":"CoRR"},{"key":"ref25","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","author":"Haarnoja"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref26"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801334.pdf?arnumber=10801334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:06:29Z","timestamp":1735196789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801334","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}