{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:48:03Z","timestamp":1773931683775,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"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":[[2023,12,5]]},"DOI":"10.1109\/ssci52147.2023.10371978","type":"proceedings-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T19:30:22Z","timestamp":1704137422000},"page":"1674-1681","source":"Crossref","is-referenced-by-count":1,"title":["Learning Control Policies for Variable Objectives from Offline Data"],"prefix":"10.1109","author":[{"given":"Marc","family":"Weber","sequence":"first","affiliation":[{"name":"Siemens AG, Technology,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phillip","family":"Swazinna","sequence":"additional","affiliation":[{"name":"Siemens AG, Technology,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Hein","sequence":"additional","affiliation":[{"name":"Siemens AG, Technology,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[{"name":"Siemens AG, Technology,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volkmar","family":"Sterzing","sequence":"additional","affiliation":[{"name":"Siemens AG, Technology,Munich,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280935"},{"key":"ref2","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"Ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref4","author":"Mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref5","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"97","author":"Fujimoto"},{"key":"ref6","author":"Levine","year":"2020","journal-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/978-3-540-74690-4_12","article-title":"Improving optimality of neural rewards regression for data-efficient batch near-optimal policy identification","volume-title":"Artificial Neural Networks - ICANN 2007","author":"Schneega\u03b2","year":"2007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368182"},{"key":"ref9","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Deisenroth","year":"2011"},{"key":"ref10","article-title":"Learning and policy search in stochastic dynamical systems with Bayesian neural networks","volume-title":"International Conference on Learning Representations","author":"Depeweg","year":"2017"},{"key":"ref11","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","author":"Wu","year":"2019","journal-title":"Behavior regularized offline reinforcement learning"},{"key":"ref13","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kumar","year":"2020"},{"key":"ref14","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Yu","year":"2020"},{"key":"ref15","first-page":"21 810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kidambi","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104366"},{"key":"ref17","first-page":"28954","article-title":"COMBO: Conservative offline model-based policy optimization","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Yu","year":"2021"},{"key":"ref18","article-title":"RAMBO-RL: Robust adversarial model-based offline reinforcement learning","author":"Rigter","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.602"},{"key":"ref20","article-title":"User-interactive offline reinforcement learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Swazinna","year":"2023"},{"key":"ref21","author":"Abdolmaleki","year":"2021","journal-title":"On multi-objective policy optimization as a tool for reinforcement learning"},{"key":"ref22","article-title":"Confidence-conditioned value functions for offline reinforcement learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hong","year":"2023"},{"key":"ref23","article-title":"Multiple-target reinforcement learning with a single policy","volume-title":"ICML 2011 Workshop on Planning and Acting with Uncertain Models","author":"Deisenroth","year":"2011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3182\/20110828-6-IT-1002.02208"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2011.5874921"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2166\/hydro.2013.169"},{"key":"ref28","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"37","author":"Schaul"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.094"},{"key":"ref30","article-title":"Temporal difference models: Model-free deep RL for model-based control","volume-title":"International Conference on Learning Representations","author":"Pong","year":"2018"},{"key":"ref31","author":"Plappert","year":"2018","journal-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref33","first-page":"7248","article-title":"RL unplugged: A suite of benchmarks for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Gulcehre","year":"2020"},{"key":"ref34","volume-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2021"},{"key":"ref35","first-page":"24753","article-title":"NeoRL: A near real-world benchmark for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Qin","year":"2022"},{"key":"ref36","author":"Brockman","year":"2016","journal-title":"Openai gym"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966389"}],"event":{"name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Mexico City, Mexico","start":{"date-parts":[[2023,12,5]]},"end":{"date-parts":[[2023,12,8]]}},"container-title":["2023 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10371778\/10371788\/10371978.pdf?arnumber=10371978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T22:11:15Z","timestamp":1705097475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10371978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ssci52147.2023.10371978","relation":{},"subject":[],"published":{"date-parts":[[2023,12,5]]}}}