{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T14:59:43Z","timestamp":1785941983933,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540938","type":"print"},{"value":"9789819540945","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4094-5_3","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:00:46Z","timestamp":1763190046000},"page":"33-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Policy Constraint by Only Support Constraint for Offline Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yunkai","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siming","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"3_CR1","unstructured":"An, G., Moon, S., Kim, J.H., Song, H.O.: Uncertainty-based offline reinforcement learning with diversified q-ensemble. In: Neural Information Processing Systems (2021). https:\/\/api.semanticscholar.org\/CorpusID:238259863"},{"key":"3_CR2","unstructured":"Bai, C., Wang, L., Yang, Z., Deng, Z., Garg, A., Liu, P., Wang, Z.: Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning. ArXiv abs\/2202.11566 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247058767"},{"key":"3_CR3","unstructured":"Chen, H., Lu, C., Ying, C., Su, H., Zhu, J.: Offline reinforcement learning via high-fidelity generative behavior modeling. ArXiv abs\/2209.14548 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252596208"},{"key":"3_CR4","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. In: Neural Information Processing Systems (2021). https:\/\/api.semanticscholar.org\/CorpusID:235294299"},{"key":"3_CR5","unstructured":"Christodoulou, P.: Soft actor-critic for discrete action settings. ArXiv abs\/1910.07207 (2019). https:\/\/api.semanticscholar.org\/CorpusID:204734462"},{"key":"3_CR6","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4RL: datasets for deep data-driven reinforcement learning (2020)"},{"key":"3_CR7","unstructured":"Fujimoto, S., Gu, S.S.: A minimalist approach to offline reinforcement learning. ArXiv abs\/2106.06860 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235422620"},{"key":"3_CR8","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning (2018). https:\/\/api.semanticscholar.org\/CorpusID:3544558"},{"key":"3_CR9","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning (2018). https:\/\/api.semanticscholar.org\/CorpusID:54457299"},{"key":"3_CR10","unstructured":"Gao, H., et\u00a0al.: Prompt-based visual alignment for zero-shot policy transfer. arXiv preprint arXiv:2406.03250 (2024)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Gao, Y., et\u00a0al.: Context shift reduction for offline meta-reinforcement learning. Adv. Neural Info. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-3505"},{"key":"3_CR12","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR13","unstructured":"Janner, M., Du, Y., Tenenbaum, J.B., Levine, S.: Planning with diffusion for flexible behavior synthesis. In: International Conference on Machine Learning (2022). https:\/\/api.semanticscholar.org\/CorpusID:248965046"},{"key":"3_CR14","unstructured":"Kalashnikov, D., Varley, J., Chebotar, Y., Swanson, B., Jonschkowski, R., Finn, C., Levine, S., Hausman, K.: MT-Opt: continuous multi-task robotic reinforcement learning at scale. arXiv preprint arXiv:2104.08212 (2021)"},{"issue":"6","key":"3_CR15","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2021","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3_CR16","unstructured":"Kostrikov, I., Fergus, R., Tompson, J., Nachum, O.: Offline reinforcement learning with fisher divergence critic regularization. In: International Conference on Machine Learning, pp. 5774\u20135783. PMLR (2021)"},{"key":"3_CR17","unstructured":"Kostrikov, I., Nair, A., Levine, S.: Offline reinforcement learning with implicit q-learning. arXiv preprint arXiv:2110.06169 (2021)"},{"key":"3_CR18","unstructured":"Kumar, A., Fu, J., Soh, M., Tucker, G., Levine, S.: Stabilizing off-policy Q-learning via bootstrapping error reduction. Adv. Neural Info. Process. Syst. 32 (2019)"},{"key":"3_CR19","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. ArXiv abs\/2006.04779 (2020). https:\/\/api.semanticscholar.org\/CorpusID:219530894"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"36507","DOI":"10.52202\/075280-1585","volume":"36","author":"S Lan","year":"2023","unstructured":"Lan, S., et al.: Contrastive modules with temporal attention for multi-task reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 36507\u201336523 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR21","unstructured":"Levine, S., Kumar, A., Tucker, G., Fu, J.: Offline reinforcement learning: tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)"},{"key":"3_CR22","unstructured":"Li, Y., Dong, J., Dong, Z., Yang, C., An, Z., Xu, Y.: SRKD: towards efficient 3D point cloud segmentation via structure-and relation-aware knowledge distillation. arXiv preprint arXiv:2506.17290 (2025)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Frequency-aligned knowledge distillation for lightweight spatiotemporal forecasting. arXiv:2507.02939 (2025)","DOI":"10.1109\/ICCV51701.2025.00682"},{"key":"3_CR24","unstructured":"Liang, Z., Mu, Y., Ding, M., Ni, F., Tomizuka, M., Luo, P.: AdaptDiffuser: diffusion models as adaptive self-evolving planners. arXiv preprint arXiv:2302.01877 (2023)"},{"key":"3_CR25","unstructured":"Lyu, J., Ma, X., Li, X., Lu, Z.: Mildly conservative q-learning for offline reinforcement learning. ArXiv abs\/2206.04745 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249605389"},{"key":"3_CR26","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"3_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129644","volume":"631","author":"Y Pan","year":"2025","unstructured":"Pan, Y., et al.: Morphology generalizable reinforcement learning via multi-level graph features. Neurocomputing 631, 129644 (2025)","journal-title":"Neurocomputing"},{"key":"3_CR28","unstructured":"Pomerleau, D.A.: ALVINN: an autonomous land vehicle in a neural network. In: NIPS (1988). https:\/\/api.semanticscholar.org\/CorpusID:18420840"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Silver, D., et\u00a0al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"key":"3_CR30","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: NIPS (2015). https:\/\/api.semanticscholar.org\/CorpusID:13936837"},{"key":"3_CR31","unstructured":"Tang, S., Wiens, J.: Model selection for offline reinforcement learning: practical considerations for healthcare settings. In: Machine Learning for Healthcare Conference, pp. 2\u201335. PMLR (2021)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"3_CR33","unstructured":"Wang, Z., Hunt, J.J., Zhou, M.: Diffusion policies as an expressive policy class for offline reinforcement learning. arXiv preprint arXiv:2208.06193 (2022)"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Wu, F., et\u00a0al.: Ocean-MBRL: offline conservative exploration for model-based offline reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 15897\u201315905 (2024)","DOI":"10.1609\/aaai.v38i14.29520"},{"key":"3_CR35","doi-asserted-by":"publisher","first-page":"31278","DOI":"10.52202\/068431-2268","volume":"35","author":"J Wu","year":"2022","unstructured":"Wu, J., Wu, H., Qiu, Z., Wang, J., Long, M.: Supported policy optimization for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 31278\u201331291 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR36","unstructured":"Wu, Y., Tucker, G., Nachum, O.: Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361 (2019)"},{"key":"3_CR37","unstructured":"Xiao, C., Wang, H., Pan, Y., White, A., White, M.: The in-sample softmax for offline reinforcement learning. ArXiv abs\/2302.14372 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257232713"},{"key":"3_CR38","unstructured":"Xu, H., Jiang, L., Li, J., Yang, Z., Wang, Z., Chan, V., Zhan, X.: Offline RL with no OOD actions: In-sample learning via implicit value regularization. ArXiv abs\/2303.15810 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257771709"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Yang, R., Bai, C., Ma, X., Wang, Z., Zhang, C., Han, L.: RORL: robust offline reinforcement learning via conservative smoothing. ArXiv abs\/2206.02829 (2022). https:\/\/api.semanticscholar.org\/CorpusID:249431425","DOI":"10.52202\/068431-1732"},{"key":"3_CR40","unstructured":"Yi, Q., et\u00a0al.: Online prototype alignment for few-shot policy transfer. In: International Conference on Machine Learning, pp. 39968\u201339983. PMLR (2023)"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, C., Wang, W., Jing, B.: Constrained policy optimization with explicit behavior density for offline reinforcement learning. Adv. Neural Info. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-0245"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4094-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T14:22:17Z","timestamp":1785939737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4094-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9789819540938","9789819540945"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4094-5_3","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}