{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:10:09Z","timestamp":1736971809374,"version":"3.33.0"},"reference-count":34,"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\/iros58592.2024.10802433","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"6840-6847","source":"Crossref","is-referenced-by-count":0,"title":["Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression"],"prefix":"10.1109","author":[{"given":"Fernando","family":"Acero","sequence":"first","affiliation":[{"name":"University College London,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[{"name":"University College London,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay7120"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2029720"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3616864"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v34i1.31470"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00752-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00701-w"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968488"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00709-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341463"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188108"},{"article-title":"Learning vision-guided dynamic locomotion over challenging terrains","year":"2021","author":"Liu","key":"ref16"},{"article-title":"Visual-locomotion: Learning to walk on complex terrains with vision","volume-title":"5th Annual Conference on Robot Learning","author":"Yu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160760"},{"key":"ref19","article-title":"Verifiable reinforcement learning via policy extraction","volume-title":"Advances in neural information processing systems","volume":"31","author":"Bastani"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04083-2_11"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-020-00175-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17360"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2022.107932"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DASC55683.2022.9925786"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636759"},{"key":"ref26","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339556"},{"article-title":"Interpretable machine learning for science with pysr and symbolicregression.jl","year":"2023","author":"Cranmer","key":"ref29"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref30"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177013604"},{"article-title":"Interpretml: A unified framework for machine learning interpretability","year":"2019","author":"Nori","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"}],"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\/10802433.pdf?arnumber=10802433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:29:33Z","timestamp":1736969373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802433","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}