{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:07:38Z","timestamp":1783490858912,"version":"3.55.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161081","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"2921-2928","source":"Crossref","is-referenced-by-count":14,"title":["Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models"],"prefix":"10.1109","author":[{"given":"Yi","family":"Liu","sequence":"first","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurav","family":"Datta","sequence":"additional","affiliation":[{"name":"UC Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ellen","family":"Novoseller","sequence":"additional","affiliation":[{"name":"Army Research Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel S.","family":"Brown","sequence":"additional","affiliation":[{"name":"University of Utah"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1262","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","author":"chen","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10269"},{"key":"ref12","first-page":"1","article-title":"Exploration by random network distillation","author":"burda","year":"0","journal-title":"the Seventh International Conference on Learning Representations"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2014.2332442"},{"key":"ref15","article-title":"Deep rein- forcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref59","article-title":"Example-driven model- based reinforcement learning for solving long-horizon visuomotor tasks","author":"wu","year":"0","journal-title":"5th Annual Conference on Robot Learning"},{"key":"ref14","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"NIPS"},{"key":"ref58","first-page":"1062","article-title":"Model-based behavioral cloning with future image similarity learning","author":"wu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref53","article-title":"Model predictive path integral control using covariance variable importance sampling","author":"williams","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref52","article-title":"Rough terrain navigation using divergence constrained model- based reinforcement learning","author":"wang","year":"0","journal-title":"5th Annual Conference on Robot Learning"},{"key":"ref11","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","author":"brown","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref55","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"wirth","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"brown","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref54","article-title":"A Bayesian approach for policy learning from trajectory preference queries","volume":"25","author":"wilson","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"1174","article-title":"Stochastic video generation with a learned prior","author":"denton","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2017.8256258"},{"key":"ref19","first-page":"1755","article-title":"Imitating latent policies from observation","author":"edwards","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"Visual foresight: Model-based deep reinforcement learning for vision- based robotic control","author":"ebert","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref51","first-page":"1439","article-title":"Entity abstraction in visual model-based reinforcement learning","author":"veerapaneni","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref45","author":"rubinstein","year":"2004","journal-title":"The Cross-Entropy Method A Unified Approach to Combinatorial Optimization Monte-Carlo Simulation and Machine Learning"},{"key":"ref48","article-title":"Benchmarks and algorithms for offline preference-based reward learning","author":"shin","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref41","first-page":"258","article-title":"Variational inference MPC for Bayesian model-based reinforcement learning","author":"okada","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1201\/9781315272610"},{"key":"ref43","first-page":"8020","article-title":"Learning human objectives by evaluating hypothetical behavior","author":"reddy","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/aa839f"},{"key":"ref8","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/B978-0-444-53859-8.00003-5","article-title":"The cross-entropy method for optimization","volume":"31","author":"botev","year":"2013","journal-title":"Handbook of Statistics"},{"key":"ref9","first-page":"1165","article-title":"Safe imitation learning via fast Bayesian reward inference from preferences","author":"brown","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"162","article-title":"Curious iLQR: Resolving uncertainty in model-based RL","author":"bechtle","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref3","article-title":"Model-based adversarial imitation learning","author":"baram","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"1177","article-title":"Asking easy questions: A user-friendly approach to active reward learning","author":"biyik","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.041"},{"key":"ref40","first-page":"1029","article-title":"Dueling posterior sampling for preference-based reinforcement learning","author":"novoseller","year":"0","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref35","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"lee","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref34","article-title":"Learning stable deep dynamics models","volume":"32","author":"kolter","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"mandlekar","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref36","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"lowrey","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581193"},{"key":"ref30","article-title":"Reward learning from human preferences and demonstrations in Atari","author":"ibarz","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"MobILE: Model-based imitation learning from observation alone","volume":"34","author":"kidambi","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Model based reinforcement learning for Atari","author":"kaiser","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref2","first-page":"390","article-title":"End-to-end differentiable adversarial imitation learning","author":"baram","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref38","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","author":"nagabandi","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25740"},{"key":"ref26","first-page":"1603","article-title":"Modelling transition dynamics in MDPs with RKHS embeddings","author":"gr\u00fcnew\u00e4lder","year":"0","journal-title":"Proceedings of the 29th International Conference on International Conference on Machine Learning"},{"key":"ref25","first-page":"48","article-title":"Learning cost functions for motion planning from human preferences","volume":"1","author":"gritsenko","year":"0","journal-title":"Proceedings of the IROS 2014 Workshop on Machine Learning in Planning and Control of Robot Motion"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509176"},{"key":"ref63","first-page":"1338","article-title":"Asynchronous methods for model-based reinforcement learning","author":"zhang","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref22","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref28","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref60","first-page":"332","article-title":"Look before you leap: Safe model-based reinforcement learning with human intervention","author":"xu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref62","first-page":"7444","article-title":"SOLAR: Deep structured representations for model-based reinforcement learning","author":"zhang","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref61","first-page":"14 129","article-title":"MOPO: Model-based offline policy optimization","volume":"33","author":"yu","year":"2020","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161081.pdf?arnumber=10161081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:37:52Z","timestamp":1690220272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161081","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}