{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T15:41:41Z","timestamp":1777650101164,"version":"3.51.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["P2SKP2_194954"],"award-info":[{"award-number":["P2SKP2_194954"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160885","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9204-9210","source":"Crossref","is-referenced-by-count":21,"title":["Benchmarking Potential Based Rewards for Learning Humanoid Locomotion"],"prefix":"10.1109","author":[{"given":"Se Hwan","family":"Jeon","sequence":"first","affiliation":[{"name":"MIT,Biomimetic Robotics Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Heim","sequence":"additional","affiliation":[{"name":"MIT,Biomimetic Robotics Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles","family":"Khazoom","sequence":"additional","affiliation":[{"name":"MIT,Biomimetic Robotics Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangbae","family":"Kim","sequence":"additional","affiliation":[{"name":"MIT,Biomimetic Robotics Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561814"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461237"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.064"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref10","article-title":"Lyapunov design for robust and efficient robotic reinforcement learning","author":"westenbroek","year":"2022","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487144"},{"key":"ref1","article-title":"Learning locomotion skills for cassie: Iterative design and sim-to-real","author":"xie","year":"2020","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530728"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3066833"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1190"},{"key":"ref18","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.061"},{"key":"ref23","article-title":"The MIT humanoid robot: Design, motion planning, and control for acrobatic behaviors","author":"chignoli","year":"2020","journal-title":"IEEE International Conference on Humanoid Robots"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041375"},{"key":"ref20","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","author":"devlin","year":"2011","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref21","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","author":"rudin","year":"2022","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.33"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9628"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2018.8581310"},{"key":"ref9","article-title":"Dynamic potential-based reward shaping","author":"devlin","year":"2012","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.04.058"},{"key":"ref3","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","author":"randl\u00f8v","year":"1998","journal-title":"ICML"},{"key":"ref6","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref5","article-title":"What matters in on-policy reinforcement learning? a large-scale empirical study","author":"andrychowicz","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160885.pdf?arnumber=10160885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:37:31Z","timestamp":1690220251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160885","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}