{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:40:31Z","timestamp":1770331231222,"version":"3.49.0"},"reference-count":47,"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\/iros55552.2023.10341990","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"7561-7567","source":"Crossref","is-referenced-by-count":1,"title":["Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores"],"prefix":"10.1109","author":[{"given":"Shukai","family":"Liu","sequence":"first","affiliation":[{"name":"University of Bristol,Department of Engineering Mathematics,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenming","family":"Wu","sequence":"additional","affiliation":[{"name":"Baidu Research,RAL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Research,RAL"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10010022"},{"key":"ref3","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89177-0_1"},{"key":"ref5","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref7","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Int. Conf. on Machine Learning","volume":"1","author":"Ng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Int. Conf. on Machine Learning","author":"Brown","year":"2019"},{"key":"ref10","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref12","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Int. Conf. on Machine Learning","volume":"1","author":"Ng"},{"key":"ref13","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. of the AAAI Conference on Artificial Intelligence (AAAI)","volume":"8","author":"Ziebart"},{"key":"ref14","article-title":"Maximum entropy deep inverse reinforcement learning","author":"Wulfmeier","year":"2015","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Int. Conf. on Machine Learning","author":"Finn","year":"2016"},{"key":"ref16","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume-title":"Int. Conf. on Artificial Intelligence","volume":"7","author":"Ramachandran","year":"2007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390175"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179129"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2891173"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref22","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Int. Conf. on Machine Learning","author":"MacGlashan","year":"2017"},{"key":"ref23","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Policy shaping with human teachers","volume-title":"Int. Conf. on Artificial Intelligence","author":"Cederborg"},{"key":"ref25","article-title":"Score-based inverse reinforcement learning","volume-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016)","author":"El Asri"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10411"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145516"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3849309"},{"key":"ref29","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Conference on robot learning","author":"Brown"},{"key":"ref31","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","author":"Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"342","article-title":"Learning multimodal rewards from rankings","volume-title":"Conference on Robot Learning","author":"Myers"},{"key":"ref33","article-title":"B-pref: Bench-marking preference-based reinforcement learning","author":"Lee","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Reward uncertainty for exploration in preference-based reinforcement learning","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981616"},{"key":"ref36","article-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","author":"Park","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1037\/14396-000"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref41","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref43","author":"Brockman","year":"2016","journal-title":"Openai gym"},{"key":"ref44","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu"},{"key":"ref45","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Int. Conf. on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"issue":"16","key":"ref47","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume-title":"KDD workshop","volume":"10","author":"Berndt","year":"1994"}],"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\/10341990.pdf?arnumber=10341990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T20:22:49Z","timestamp":1705004569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341990","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}