{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:09:38Z","timestamp":1766138978893,"version":"3.32.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2024,11,22]]},"DOI":"10.1109\/humanoids58906.2024.10769835","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T18:54:29Z","timestamp":1733252069000},"page":"205-212","source":"Crossref","is-referenced-by-count":3,"title":["Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion"],"prefix":"10.1109","author":[{"given":"Henri-Jacques","family":"Gei\u03b2","sequence":"first","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Firas","family":"Al-Hafez","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andre","family":"Seyfarth","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Human Sciences Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Tateo","sequence":"additional","affiliation":[{"name":"Technical University Darmstadt,Computer Science Department"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Eleventh International Conference on Learning Representations (ICLR)","author":"Al-Hafez","article-title":"Ls-iq: Implicit reward regularization for inverse reinforcement learning","key":"ref1"},{"volume-title":"6th Robot Learning Workshop","author":"Al-Hafez","article-title":"Locomujoco: A comprehensive imitation learning benchmark for locomotion","key":"ref2"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/Humanoids43949.2019.9035034"},{"key":"ref4","article-title":"Sar: Generalization of physiological agility and dexterity via synergistic action representation","author":"Berg","year":"2023","journal-title":"arXiv preprint arXiv:2307.03716"},{"key":"ref5","article-title":"Myosuite-a contact-rich simulation suite for musculoskeletal motor control","volume-title":"Proceedings of Machine Learning Research","volume":"168","author":"Caggiano"},{"key":"ref6","article-title":"Latent exploration for reinforcement learning","volume":"36","author":"Chiappa","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"International conference on machine learning","author":"Chou"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1523\/JNEUROSCI.6344-11.2012"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1152\/jn.00825.2009"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TNSRE.2021.3063015"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TBME.2007.901024"},{"key":"ref12","first-page":"9828","article-title":"Co-adaptation of algorithmic and implementational innovations in inference-based deep reinforcement learning","volume":"34","author":"Furuta","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Iq-learn: Inverse soft-q learning for imitation","author":"Garg","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TNSRE.2010.2047592"},{"key":"ref15","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"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/j.jbiomech.2010.06.025"},{"key":"ref17","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ECTI-CON54298.2022.9795606"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-319-94042-7_7"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1007\/978-3-030-29135-8_4"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/3306346.3322972"},{"key":"ref22","first-page":"14656","article-title":"What matters for adversarial imitation learning?","volume":"34","author":"Orsini","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"1","article-title":"Phil Sik Chang, Jaedong Lee, Moon Seok Park, and Jehee Lee. Generative gaitnet","volume-title":"ACM SIGGRAPH 2022 Conference Proceedings","author":"Park"},{"volume-title":"International Conference on Learning Representations","author":"Peng","article-title":"Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow","key":"ref24"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1145\/3099564.3099567"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1002\/cav.2092"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/TBME.2016.2586891"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1145\/279943.279964"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International Conference on Machine Learning","author":"Schulman"},{"year":"2023","author":"Schumacher","article-title":"Natural and robust walking using reinforcement learning without demonstrations in high-dimensional musculoskeletal models","key":"ref30"},{"volume-title":"The Eleventh International Conference on Learning Representations","author":"Schumacher","article-title":"Dep-rl: Embodied exploration for reinforcement learning in overactuated and musculoskeletal systems","key":"ref31"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1101\/2020.08.11.246801"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/IROS.2012.6386109"},{"year":"2019","author":"Torabi","article-title":"Generative adversarial imitation from observation","key":"ref34"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1103\/PhysRev.36.823"}],"event":{"name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2024,11,22]]},"location":"Nancy, France","end":{"date-parts":[[2024,11,24]]}},"container-title":["2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10769770\/10769590\/10769835.pdf?arnumber=10769835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T19:56:40Z","timestamp":1736539000000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/humanoids58906.2024.10769835","relation":{},"subject":[],"published":{"date-parts":[[2024,11,22]]}}}