{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T17:06:52Z","timestamp":1789405612155,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032384034","type":"print"},{"value":"9783032384041","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-38404-1_3","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T16:46:22Z","timestamp":1789404382000},"page":"27-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Regularized Policy Iteration Under Transition Uncertainty"],"prefix":"10.1007","author":[{"given":"Hongqiang","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghui","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiding","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"3_CR1","unstructured":"Dong, J., Li, J., Wang, B., Zhang, J.: Online policy optimization for robust Markov decision process. Uncertainty Artif. Intell. (2024)"},{"key":"3_CR2","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4RL: datasets for deep data-driven reinforcement learning. arXiv (2020)"},{"key":"3_CR3","unstructured":"Ghosh, D., Ajay, A., Agrawal, P., Levine, S.: Offline RL policies should be trained to be adaptive. In: International Conference on Machine Learning (2022)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Gottesman, O., et al.: Guidelines for reinforcement learning in healthcare. Nat. Med. (2019)","DOI":"10.1038\/s41591-018-0310-5"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Guo, K., Yunfeng, S., Geng, Y.: Model-based offline reinforcement learning with pessimism-modulated dynamics belief. Adv. Neural Inf. Process. Syst. (2022)","DOI":"10.52202\/068431-0033"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Huang, L., Dong, B., Zhang, W.: Efficient offline reinforcement learning with relaxed conservatism. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3364844"},{"key":"3_CR7","unstructured":"Kidambi, R., Rajeswaran, A., Netrapalli, P., Joachims, T.: MOReL: model-based offline reinforcement learning. Adv. Neural Inf. Process. Syst. (2020)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Kumar, A., et al.: Pre-training for robots: offline RL enables learning new tasks from a handful of trials. arXiv (2022). https:\/\/arxiv.org\/abs\/2210.05178","DOI":"10.15607\/RSS.2023.XIX.019"},{"key":"3_CR9","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. Adv. Neural Inf. Process. Syst. (2020)"},{"key":"3_CR10","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv (2020). https:\/\/arxiv.org\/abs\/2005.01643"},{"key":"3_CR11","unstructured":"Lin, H., et al.: Any-step dynamics model improves future predictions for online and offline reinforcement learning. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"3_CR12","unstructured":"Lin, H., Wang, P., Zheng, N.: Regularized offline policy optimization with posterior hybrid Bayesian belief. arXiv preprint arXiv:2606.00680 (2026)"},{"key":"3_CR13","unstructured":"Lin, H., Zhang, D., Sun, Y., Li, M., Yang, N., Zhang, H.: Offline policy optimization with posterior sampling. arXiv (2026). https:\/\/arxiv.org\/abs\/2605.07393"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Q., Liu, Z., Mo, D., Yu, C.: An offline adaptation framework for constrained multi-objective reinforcement learning. Adv. Neural Inf. Process. Syst. (2024)","DOI":"10.52202\/079017-4453"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, F., Zhu, H.: Optimized supervised control of stochastic timed discrete event systems using supervisory control theory and reinforcement learning. In: International Conference on Artificial Neural Networks, pp. 402\u2013414 (2025)","DOI":"10.1007\/978-3-032-04555-3_33"},{"key":"3_CR16","unstructured":"Lu, C., Ball, P., Parker-Holder, J., Osborne, M., Roberts, S.J.: Revisiting design choices in offline model based reinforcement learning. In: International Conference on Learning Representations (2022)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Mao, Y., Wang, Q., Qu, Y., Jiang, Y., Ji, X.: Doubly mild generalization for offline reinforcement learning. Adv. Neural Inf. Process. Syst. (2024)","DOI":"10.52202\/079017-1628"},{"key":"3_CR18","unstructured":"Park, K., Lee, Y.: Model-based offline reinforcement learning with lower expectile q-learning. In: International Conference on Learning Representations (2025)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Park, S., Frans, K., Levine, S., Kumar, A.: Is value learning really the main bottleneck in offline RL? Adv. Neural Inf. Process. Syst. (2024)","DOI":"10.52202\/079017-2509"},{"key":"3_CR20","unstructured":"Prudencio, R.F., Maximo, M.R., Colombini, E.L.: A survey on offline reinforcement learning: taxonomy, review, and open problems. IEEE Trans. Neural Netw. Learn. Syst. (2023)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Qiao, Z., Lyu, J., Jiao, K., Liu, Q., Li, X.: SUMO: search-based uncertainty estimation for model-based offline reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (2025)","DOI":"10.1609\/aaai.v39i19.34206"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Rigter, M., Lacerda, B., Hawes, N.: Rambo-rl: robust adversarial model-based offline reinforcement learning. Adv. Neural Inf. Process. Syst. (2022)","DOI":"10.52202\/068431-1170"},{"key":"3_CR23","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning (2015)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Hyperpoint: multimodal 3d foundation model in hyperbolic space. Pattern Recogn. (2026)","DOI":"10.1016\/j.patcog.2025.112800"},{"key":"3_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"key":"3_CR26","unstructured":"Wu, Y., Tucker, G., Nachum, O.: Behavior regularized offline reinforcement learning. ArXiv (2019)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Yeom, J., Jo, Y., Kim, J., Lee, S., Han, S.: Exclusively penalized Q-learning for offline reinforcement learning. Adv. Neural Inf. Process. Syst. (2024)","DOI":"10.52202\/079017-3603"},{"key":"3_CR28","unstructured":"Yu, T., Kumar, A., Rafailov, R., Rajeswaran, A., Levine, S., Finn, C.: COMBO: conservative offline model-based policy optimization. Adv. Neural Inf. Process. Syst. (2021)"},{"key":"3_CR29","unstructured":"Yu, T., et al.: MOPO: model-based offline policy optimization. Adv. Neural Inf. Process. Syst. (2020)"},{"key":"3_CR30","unstructured":"Zhang, D., et al.: Not all queries need deep thought: coficot for adaptive coarse-to-fine stateful refinement. arXiv preprint arXiv:2603.08251 (2026)"},{"key":"3_CR31","unstructured":"Zhang, D., et al.: Pointcot: a multi-modal benchmark for explicit 3d geometric reasoning. arXiv (2026)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: Igasa: integrated geometry-aware and skip-attention modules for enhanced point cloud registration. IEEE Trans. Circ. Syst. Video Technol. (2026)","DOI":"10.1109\/TCSVT.2026.3656975"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Tan, X.: Adaptive reward shifting based on behavior proximity for offline reinforcement learning. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (2023)","DOI":"10.24963\/ijcai.2023\/514"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38404-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T16:46:39Z","timestamp":1789404399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38404-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"ISBN":["9783032384034","9783032384041"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38404-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"assertion":[{"value":"15 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Padua","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}