{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T22:21:45Z","timestamp":1767651705385,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611629","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5083-5089","source":"Crossref","is-referenced-by-count":3,"title":["Learning Diverse Skills for Local Navigation under Multi-constraint Optimality"],"prefix":"10.1109","author":[{"given":"Jin","family":"Cheng","sequence":"first","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Germany"}]},{"given":"Marin","family":"Vlastelica","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Germany"}]},{"given":"Pavel","family":"Kolev","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Germany"}]},{"given":"Chenhao","family":"Li","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Germany"}]},{"given":"Georg","family":"Martius","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"article-title":"Discovering policies with domino: Diversity optimization maintaining near optimality","year":"2022","author":"Zahavy","key":"ref4"},{"article-title":"Diversity is all you need: Learning skills without a reward function","year":"2018","author":"Eysenbach","key":"ref5"},{"article-title":"Fast task inference with variational intrinsic successor features","volume-title":"International Conference on Learning Representations","author":"Hansen","key":"ref6"},{"article-title":"Learning more skills through optimistic exploration","volume-title":"International Conference on Learning Representations","author":"Strouse","key":"ref7"},{"article-title":"Variational intrinsic control","volume-title":"International Conference on Learning Representations, Workshop Track Proceedings","author":"Gregor","key":"ref8"},{"article-title":"Dynamics-aware unsupervised discovery of skills","year":"2019","author":"Sharma","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref12","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981198"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref16","first-page":"342","article-title":"Learning agile skills via adversarial imitation of rough partial demonstrations","volume-title":"Conference on Robot Learning","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160562"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3307008"},{"article-title":"Diverse offline imitation learning","volume-title":"Second Agent Learning in Open-Endedness Workshop","author":"Vlastelica","key":"ref19"},{"key":"ref20","first-page":"8198","article-title":"One solution is not all you need: Few-shot extrapolation via structured maxent rl","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160421"},{"article-title":"Lipschitz-constrained unsupervised skill discovery","volume-title":"International Conference on Learning Representations","author":"Park","key":"ref22"},{"article-title":"Controllability-aware unsupervised skill discovery","year":"2023","author":"Park","key":"ref23"},{"key":"ref24","volume-title":"Constrained Markov decision processes.","volume":"7","author":"Altman","year":"1999"},{"key":"ref25","article-title":"Constrained mdps and the reward hypothesis","volume-title":"Musings about machine learning and other things (blog)","author":"Szepesv\u00e1ri","year":"2020"},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming.","year":"2014","author":"Puterman","key":"ref26"},{"key":"ref27","first-page":"25746","article-title":"Reward is enough for convex mdps","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual","author":"Zahavy"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref29","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID lagrangian methods","volume-title":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event","volume":"119","author":"Stooke"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref31","article-title":"Successor features for transfer in reinforcement learning","volume":"30","author":"Barreto","year":"2017","journal-title":"Advances in neural information processing systems"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref32"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref33"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref34"},{"key":"ref35","first-page":"1407","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"International conference on machine learning","author":"Espeholt"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561559"},{"article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref37"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611629.pdf?arnumber=10611629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:08:37Z","timestamp":1723349317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611629","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}