{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:47:18Z","timestamp":1778258838208,"version":"3.51.4"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128707","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"14999-15006","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccer"],"prefix":"10.1109","author":[{"given":"Adam","family":"Labiosa","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihan","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhant","family":"Agarwal","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Cong","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geethika","family":"Hemkumar","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav Narayan","family":"Harish","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josh","family":"Kelle","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zisen","family":"Shao","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josiah P.","family":"Hanna","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Solving rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref3","volume-title":"Achieving human level competitive robot table tennis","author":"D\u2019Ambrosio","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i3.2549"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/267658.267738"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3151771"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3120628"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843623500135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793864"},{"key":"ref14","article-title":"Multiagent manipulation via locomotion using hierarchical sim2real","author":"Nachum","year":"2019","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196642"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062342"},{"key":"ref17","first-page":"859","article-title":"Rethinking sim2real: Lower fidelity simulation leads to higher sim2real transfer in navigation","volume-title":"Conference on Robot Learning","author":"Truong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01048-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2419431"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127963"},{"key":"ref23","article-title":"Black-box safety validation of autonomous systems: A multi-fidelity reinforcement learning approach","author":"Beard","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2020.2977971"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/02783649251364393"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3065410"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09603-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3075065"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"key":"ref30","volume-title":"Designing a skilled soccer team for robocup: Exploring skill-set-primitives through reinforcement learning","author":"Abreu","year":"2023"},{"key":"ref31","volume-title":"Tikick: Towards playing multi-agent football full games from single-agent demonstrations","author":"Huang","year":"2021"},{"key":"ref32","volume-title":"Tizero: Mastering multi-agent football with curriculum learning and self-play","author":"Lin","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abo0235"},{"key":"ref34","article-title":"Emergent coordination through competition","author":"Liu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-021-01333-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45603-1_56"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341936"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981984"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2009.02.004"},{"key":"ref43","volume-title":"B-Human code release documentation 2023","author":"R\u00f6fer","year":"2023"},{"key":"ref44","article-title":"Learning robot soccer from egocentric vision with deep reinforcement learning","author":"Tirumala","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"issue":"268","key":"ref46","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128707.pdf?arnumber=11128707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:08:40Z","timestamp":1756879720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128707","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}