{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T14:57:31Z","timestamp":1776956251582,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342272","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"7501-7507","source":"Crossref","is-referenced-by-count":3,"title":["Learning to Solve Tasks with Exploring Prior Behaviours"],"prefix":"10.1109","author":[{"given":"Ruiqi","family":"Zhu","sequence":"first","affiliation":[{"name":"King's College London,Department of Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Aberdeen,Department of Computing Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oya","family":"Celiktutan","sequence":"additional","affiliation":[{"name":"King's College London,Department of Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.073"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.31256\/HSMR2022.25"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3054625"},{"key":"ref6","article-title":"Cog: Connecting new skills to past experience with offline reinforcement learning","author":"Singh","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","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":"ref8","article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Lillicrap","year":"2016"},{"key":"ref9","article-title":"Active hierarchical exploration with stable subgoal representation learning","volume-title":"International Conference on Learning Representations","author":"Li","year":"2022"},{"key":"ref10","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ross","year":"2011"},{"key":"ref11","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70139-4","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume":"30","author":"Li","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"537","article-title":"Xirl: Cross-embodiment inverse reinforcement learning","volume-title":"Conference on Robot Learning","author":"Zakka","year":"2022"},{"key":"ref14","article-title":"Demonstration-guided reinforcement learning with learned skills","volume-title":"Conference on Robot Learning","author":"Pertsch","year":"2021"},{"key":"ref15","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Singh","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref17","article-title":"Hind-sight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref19","article-title":"Exploration by random network distillation","volume-title":"International Conference on Learning Representations","author":"Burda","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636536"},{"key":"ref21","article-title":"Never give up: Learning directed exploration strategies","volume-title":"International Conference on Learning Representations","author":"Badia","year":"2020"},{"key":"ref22","article-title":"Ride: Rewarding impact-driven exploration for procedurally-generated environments","volume-title":"International Conference on Learning Representations","author":"Raileanu","year":"2020"},{"key":"ref23","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"International Conference on Machine Learning","author":"Ostrovski","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/406"},{"key":"ref25","article-title":"Replacing rewards with examples: Example-based policy search via recursive classification","volume":"34","author":"Eysenbach","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"C-learning: Learning to achieve goals via recursive classification","volume-title":"International Conference on Learning Representations","author":"Eysenbach","year":"2021"},{"key":"ref27","article-title":"Off-policy actor-critic","volume-title":"International Conference on Machine Learning","author":"Degris","year":"2012"},{"key":"ref28","article-title":"Bebold: Exploration beyond the boundary of explored regions","author":"Zhang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref30","first-page":"7750","article-title":"Maximum entropy gain exploration for long horizon multi-goal reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pitis","year":"2020"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342272.pdf?arnumber=10342272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:16:08Z","timestamp":1703013368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342272","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}