{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:36:47Z","timestamp":1757608607538,"version":"3.44.0"},"reference-count":38,"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"}],"funder":[{"DOI":"10.13039\/501100009327","name":"Pazy","doi-asserted-by":"publisher","award":["195-2020"],"award-info":[{"award-number":["195-2020"]}],"id":[{"id":"10.13039\/501100009327","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2246221"],"award-info":[{"award-number":["2246221"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128350","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1177-1183","source":"Crossref","is-referenced-by-count":0,"title":["SuPLE: Robot Learning with Lyapunov Rewards"],"prefix":"10.1109","author":[{"given":"Phu","family":"Nguyen","sequence":"first","affiliation":[{"name":"Davidson College of Engineering, San Jose State University,Computer Engineering Dept.,CA,USA,95192"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Polani","sequence":"additional","affiliation":[{"name":"University of Hertfordshire,Department of Computer Science,UK,AL10 9AB"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stas","family":"Tiomkin","sequence":"additional","affiliation":[{"name":"Texas Tech University,Department of Computer Science,TX,USA,79409"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2004.1383932"},{"issue":"2","key":"ref2","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/S0005-1098(99)00140-5","article-title":"Swinging up a pendulum by energy control","volume":"36","author":"\u00c5str\u00f6m","year":"2000","journal-title":"Automatica"},{"issue":"1","key":"ref3","first-page":"2810","article-title":"Robust swing-up control for a rotational double pendulum","volume-title":"IFAC Proceedings Volumes","volume":"29","author":"Bortoff","year":"1996"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2018.8623253"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10156044"},{"key":"ref7","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proceedings of the 16th International Conference on Machine Learning","volume":"99","author":"Ng","year":"1999"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC62350.2024.10587783"},{"key":"ref9","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the 28th International Conference on machine learning (ICML-11)","author":"Deisenroth","year":"2011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(85)90011-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10087-8"},{"key":"ref12","article-title":"Adversarial imitation via variational inverse reinforcement learning","volume-title":"International Conference Learning Representation, ICLR2019","author":"Qureshi","year":"2019"},{"key":"ref13","article-title":"Variational intrinsic control revisited","volume-title":"International Conference on Learning Representations","author":"Kwon","year":"2021"},{"key":"ref14","article-title":"Efficient empowerment estimation for unsupervised stabilization","volume-title":"International Conference Learning Representations","author":"Zhao","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2018.10.049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2017.00025"},{"key":"ref17","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"Mohamed","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"International Conference on Learning Representations, (ICLR)","volume":"2021","author":"Sharma","year":"2019"},{"key":"ref19","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"International Conference on Learning Representations, (ICLR)","volume":"2019","author":"Eysenbach","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53734-9_4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554676"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/1059712310392389"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0004018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC58415.2024.10920268"},{"issue":"2","key":"ref25","first-page":"824","article-title":"Entropy and mutual information for markov channels with general inputs","volume-title":"Proceedings of the annual Allerton conference on communication control and computing","volume":"40","author":"Holliday","year":"2002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2005.1582414"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PRXLife.2.033009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.110.168702"},{"key":"ref29","article-title":"Variational intrinsic control","author":"Gregor","year":"2016","journal-title":"arXiv preprint"},{"issue":"3","key":"ref30","first-page":"78","article-title":"Numerical calculation of lyapunov exponents","volume":"6","author":"Sandri","year":"1996","journal-title":"Mathematica Journal"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1201\/9780429492563"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1515\/zna-1981-0115"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142993247311"},{"key":"ref34","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","year":"2018"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/S0036142993247311"},{"key":"ref37","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.831187"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128350.pdf?arnumber=11128350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:07:32Z","timestamp":1756879652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128350","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}