{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T03:56:04Z","timestamp":1774583764500,"version":"3.50.1"},"reference-count":54,"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\/iros58592.2024.10802334","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"13303-13310","source":"Crossref","is-referenced-by-count":22,"title":["CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Elliot","family":"Chane-Sane","sequence":"first","affiliation":[{"name":"Université de Toulouse,LAAS-CNRS,Toulouse,France,31400"}]},{"given":"Pierre-Alexandre","family":"Leziart","sequence":"additional","affiliation":[{"name":"Université de Toulouse,LAAS-CNRS,Toulouse,France,31400"}]},{"given":"Thomas","family":"Flayols","sequence":"additional","affiliation":[{"name":"Université de Toulouse,LAAS-CNRS,Toulouse,France,31400"}]},{"given":"Olivier","family":"Stasse","sequence":"additional","affiliation":[{"name":"Université de Toulouse,LAAS-CNRS,Toulouse,France,31400"}]},{"given":"Philippe","family":"Sou\u00e8res","sequence":"additional","affiliation":[{"name":"Université de Toulouse,LAAS-CNRS,Toulouse,France,31400"}]},{"given":"Nicolas","family":"Mansard","sequence":"additional","affiliation":[{"name":"Université de Toulouse,LAAS-CNRS,Toulouse,France,31400"}]}],"member":"263","reference":[{"key":"ref1","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on Robot Learning","author":"Agarwal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref4","article-title":"Robot parkour learning","author":"Zhuang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981973"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342271"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref11","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375154"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3218167"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1241826"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561559"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000129"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981539"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192581"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400935"},{"key":"ref21","article-title":"Evaluation of constrained reinforcement learning algorithms for legged locomotion","author":"Lee","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.056"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38259-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375148"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref32","article-title":"Brax - a differentiable physics engine for large scale rigid body simulation","author":"Freeman","year":"2021"},{"key":"ref33","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref34","article-title":"Minimizing energy consumption leads to the emergence of gaits in legged robots","author":"Fu","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982132"},{"key":"ref36","article-title":"Learning vision-based bipedal locomotion for challenging terrain","author":"Duan","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976639"},{"key":"ref38","article-title":"Proxddp: Proximal constrained trajectory optimization","author":"Jallet","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-020-00179-2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197371"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982038"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3351797"},{"key":"ref46","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","author":"Chow","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref47","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018"},{"key":"ref48","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref51","article-title":"Constrained mdps can be solved by eearly-termination with recurrent models","volume-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop","author":"Sun"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.1.73"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1137\/050622328"},{"key":"ref54","article-title":"rl-games: A high-performance framework for reinforcement learning","author":"Makoviichuk","year":"2021"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"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\/10802334.pdf?arnumber=10802334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:33Z","timestamp":1735196433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802334","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}