{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:54:02Z","timestamp":1766159642155,"version":"3.38.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10885921","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"1147-1152","source":"Crossref","is-referenced-by-count":3,"title":["A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations"],"prefix":"10.1109","author":[{"given":"Erhan Can","family":"Ozcan","sequence":"first","affiliation":[{"name":"Boston University,Division of Systems Engineering,Boston,MA,USA,02215"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vittorio","family":"Giammarino","sequence":"additional","affiliation":[{"name":"Boston University,Division of Systems Engineering,Boston,MA,USA,02215"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Queeney","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA,02139"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis Ch.","family":"Paschalidis","sequence":"additional","affiliation":[{"name":"Boston University,Division of Systems Engineering,Department of Electrical and Computer Engineering, Department of Biomedical Engineering,Boston,MA,USA,02215"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint arXiv:1509.02971"},{"key":"ref5","article-title":"Maximum a posteriori policy optimisation","author":"Abdolmaleki","year":"2018","journal-title":"arXiv preprint arXiv:1806.06920"},{"key":"ref6","first-page":"11 909","article-title":"Generalized proximal policy optimization with sample reuse","volume":"34","author":"Queeney","year":"2021","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Optimal transport perturbations for safe reinforcement learning with robustness guarantees","author":"Queeney","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref11","article-title":"Imitation learning: Progress, taxonomies and challenges","author":"Zheng","year":"2021","journal-title":"arXiv preprint arXiv:2106.12177"},{"key":"ref12","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv preprint arXiv:1801.00690"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref14","article-title":"Reinforcement learning from imperfect demonstrations","author":"Gao","year":"2018","journal-title":"arXiv preprint arXiv:1802.05313"},{"key":"ref15","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv preprint arXiv:2006.09359"},{"key":"ref16","article-title":"Offline reinforcement learning with soft behavior regularization","author":"Xu","year":"2021","journal-title":"arXiv preprint arXiv:2110.07395"},{"key":"ref17","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"In Proceedings of the 33rd International Conference on Machine Learning","author":"Finn"},{"key":"ref18","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Model-based adversarial imitation learning","author":"Baram","year":"2016","journal-title":"arXiv preprint arXiv:1612.02179"},{"key":"ref20","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018","journal-title":"arXiv preprint arXiv:1807.06158"},{"key":"ref21","first-page":"6036","article-title":"Provably efficient imitation learning from observation alone","volume-title":"In Proceedings of the 36th International Conference on Machine Learning","author":"Sun"},{"key":"ref22","first-page":"28 598","article-title":"Mobile: Model-based imitation learning from observation alone","volume":"34","author":"Kidambi","year":"2021","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"Adversarial imitation learning from visual observations using latent information","author":"Giammarino","year":"2023","journal-title":"arXiv preprint arXiv:2309.17371"},{"key":"ref24","article-title":"Visual imitation learning with patch rewards","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2302.00965"},{"key":"ref25","article-title":"Inverse reinforcement learning for video games","author":"Tucker","year":"2018","journal-title":"arXiv preprint arXiv:1810.10593"},{"key":"ref26","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"In Proceedings of the 36th International Conference on Machine Learning","author":"Brown"},{"key":"ref27","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics","author":"Ross"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.038"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2866455"},{"key":"ref30","first-page":"1755","article-title":"Imitating latent policies from observation","volume-title":"In Proceedings of the 36th International Conference on Machine Learning","author":"Edwards"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487167"},{"key":"ref33","article-title":"Fast policy learning through imitation and reinforcement","author":"Cheng","year":"2018","journal-title":"arXiv preprint arXiv:1805.10413"},{"key":"ref34","article-title":"Combining imitation and deep reinforcement learning to human-level performance on a virtual foraging task","author":"Giammarino","year":"2023","journal-title":"Adaptive Behavior"},{"key":"ref35","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","author":"Goecks","year":"2019","journal-title":"arXiv preprint arXiv:1910.04281"},{"key":"ref36","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","volume":"29","author":"Agrawal","year":"2016","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"In Proceedings of the 4th Conference on Robot Learning","author":"Nagabandi"},{"key":"ref38","first-page":"7953","article-title":"A game theoretic framework for model based reinforcement learning","volume-title":"In Proceedings of the 37th International Conference on Machine Learning","author":"Rajeswaran"},{"key":"ref39","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"Janner","year":"2019","journal-title":"In Advances in Neural Information Processing Systems"},{"volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","year":"2010","author":"Ziebart","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref42","article-title":"A model-based approach for improving reinforcement learning efficiency leveraging expert observations","author":"Ozcan","year":"2024","journal-title":"arXiv preprint arXiv:2402.18836"},{"key":"ref43","first-page":"21 810","article-title":"Morel: Model-based offline reinforcement learning","volume":"33","author":"Kidambi","year":"2020","journal-title":"In Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","start":{"date-parts":[[2024,12,16]]},"location":"Milan, Italy","end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10885921.pdf?arnumber=10885921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:23:34Z","timestamp":1740641014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10885921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10885921","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}