{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:22:30Z","timestamp":1787404950942,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540907","type":"print"},{"value":"9789819540914","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"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\/978-981-95-4091-4_30","type":"book-chapter","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T20:07:58Z","timestamp":1762632478000},"page":"435-450","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Context-Aware Policy-Guided Gradient Search for\u00a0Offline Model-Based Optimization"],"prefix":"10.1007","author":[{"given":"Mingcheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"issue":"6","key":"30_CR1","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1214\/aos\/1176345637","volume":"9","author":"PJ Bickel","year":"1981","unstructured":"Bickel, P.J., Freedman, D.A.: Some asymptotic theory for the bootstrap. Ann. Stat. 9(6), 1196\u20131217 (1981)","journal-title":"Ann. Stat."},{"key":"30_CR2","unstructured":"Brookes, D.H., Park, H., Listgarten, J.: Conditioning by adaptive sampling for robust design. In: ICML (2019)"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Chemingui, Y., Deshwal, A., Hoang, T.N., Doppa, J.R.: Offline model-based optimization via policy-guided gradient search. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i10.29001"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhang, Y., Fu, J., Liu, X.S., Coates, M.: Bidirectional learning for offline infinite-width model-based optimization. In: NeurIPS (2022)","DOI":"10.52202\/068431-2136"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: ROMO: retrieval-enhanced offline model-based optimization. In: DAI (2023)","DOI":"10.1145\/3627676.3627685"},{"key":"30_CR6","unstructured":"Fannjiang, C., Listgarten, J.: Autofocused oracles for model-based design. In: NeurIPS (2020)"},{"key":"30_CR7","unstructured":"Fu, J., Levine, S.: Offline model-based optimization via normalized maximum likelihood estimation. In: ICLR (2021)"},{"key":"30_CR8","unstructured":"Fujimoto, S., Gu, S.S.: A minimalist approach to offline reinforcement learning. In: NeurIPS (2021)"},{"key":"30_CR9","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: ICML (2019)"},{"issue":"9","key":"30_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2020.100142","volume":"1","author":"W Gao","year":"2020","unstructured":"Gao, W., Mahajan, S.P., Sulam, J., Gray, J.J.: Deep learning in protein structural modeling and design. Patterns 1(9), 100142 (2020)","journal-title":"Patterns"},{"key":"30_CR11","unstructured":"Ghaffari, S., Saleh, E., Schwing, A.G., Wang, Y., Burke, M.D., Sinha, S.: Robust model-based optimization for challenging fitness landscapes. In: ICLR (2024)"},{"key":"30_CR12","unstructured":"Hafner, D., Lillicrap, T.P., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. In: ICLR (2020)"},{"issue":"11","key":"30_CR13","doi-asserted-by":"publisher","first-page":"2414","DOI":"10.2514\/1.J052732","volume":"52","author":"W Hoburg","year":"2014","unstructured":"Hoburg, W., Abbeel, P.: Geometric programming for aircraft design optimization. AIAA J. 52(11), 2414\u20132426 (2014)","journal-title":"AIAA J."},{"issue":"5","key":"30_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3451179","volume":"26","author":"G Huang","year":"2021","unstructured":"Huang, G., et al.: Machine learning for electronic design automation: a survey. ACM Trans. Des. Autom. Electron. Syst. 26(5), 1\u201346 (2021)","journal-title":"ACM Trans. Des. Autom. Electron. Syst."},{"key":"30_CR15","unstructured":"Kidambi, R., Rajeswaran, A., Netrapalli, P., Joachims, T.: MOReL: model-based offline reinforcement learning. In: NeurIPS (2020)"},{"key":"30_CR16","unstructured":"Kirjner, A., et al.: Improving protein optimization with smoothed fitness landscapes. In: ICLR (2024)"},{"key":"30_CR17","unstructured":"Kong, L., et\u00a0al.: Diffusion models as constrained samplers for optimization with unknown constraints. arXiv:2402.18012 (2024)"},{"key":"30_CR18","unstructured":"Kostrikov, I., Nair, A., Levine, S.: Offline reinforcement learning with implicit Q-learning. In: ICLR (2022)"},{"key":"30_CR19","unstructured":"Krishnamoorthy, S., Mashkaria, S.M., Grover, A.: Diffusion models for black-box optimization. In: ICML (2023)"},{"key":"30_CR20","unstructured":"Kumar, A., Fu, J., Soh, M., Tucker, G., Levine, S.: Stabilizing off-policy Q-learning via bootstrapping error reduction. In: NeurIPS (2019)"},{"key":"30_CR21","unstructured":"Kumar, A., Levine, S.: Model inversion networks for model-based optimization. In: NeurIPS (2020)"},{"key":"30_CR22","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. In: NeurIPS (2020)"},{"key":"30_CR23","unstructured":"Mashkaria, S.M., Krishnamoorthy, S., Grover, A.: Generative pretraining for black-box optimization. In: ICML (2023)"},{"key":"30_CR24","unstructured":"Nair, A., Dalal, M., Gupta, A., Levine, S.: Accelerating online reinforcement learning with offline datasets. arXiv:2006.09359 (2020)"},{"key":"30_CR25","unstructured":"Osband, I., Aslanides, J., Cassirer, A.: Randomized prior functions for deep reinforcement learning. In: NeurIPS (2018)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley Series in Probability and Statistics. Wiley (1994)","DOI":"10.1002\/9780470316887"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Qi, H., Su, Y., Kumar, A., Levine, S.: Data-driven offline decision-making via invariant representation learning. In: NeurIPS (2022)","DOI":"10.52202\/068431-0961"},{"issue":"5","key":"30_CR28","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/s41573-019-0050-3","volume":"19","author":"P Schneider","year":"2020","unstructured":"Schneider, P., et al.: Rethinking drug design in the artificial intelligence era. Nat. Rev. Drug Discovery 19(5), 353\u2013364 (2020)","journal-title":"Nat. Rev. Drug Discovery"},{"issue":"1","key":"30_CR29","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","volume":"104","author":"B Shahriari","year":"2016","unstructured":"Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., de Freitas, N.: Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104(1), 148\u2013175 (2016)","journal-title":"Proc. IEEE"},{"key":"30_CR30","unstructured":"Trabucco, B., Geng, X., Kumar, A., Levine, S.: Design-bench: benchmarks for data-driven offline model-based optimization. In: ICML (2022)"},{"key":"30_CR31","unstructured":"Trabucco, B., Kumar, A., Geng, X., Levine, S.: Conservative objective models for effective offline model-based optimization. In: ICML (2021)"},{"key":"30_CR32","unstructured":"Wang, T., Du, S.S., Torralba, A., Isola, P., Zhang, A., Tian, Y.: Denoised MDPs: learning world models better than the world itself. In: ICML (2022)"},{"issue":"6","key":"30_CR33","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2740-6","volume":"17","author":"T Wu","year":"2023","unstructured":"Wu, T., Qian, H., Liu, Z., Zhou, J., Zhou, A.: Bi-objective evolutionary Bayesian network structure learning via skeleton constraint. Front. Comp. Sci. 17(6), 176350 (2023)","journal-title":"Front. Comp. Sci."},{"key":"30_CR34","unstructured":"Yu, P., et\u00a0al.: Latent energy-based odyssey: Black-box optimization via expanded exploration in the energy-based latent space. arXiv:2405.16730 (2024)"},{"key":"30_CR35","unstructured":"Yu, S., Ahn, S., Song, L., Shin, J.: RoMA: robust model adaptation for offline model-based optimization. In: NeurIPS (2021)"},{"key":"30_CR36","unstructured":"Yu, T., et al.: MOPO: model-based offline policy optimization. In: NeurIPS (2020)"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Yun, T., Yun, S., Lee, J., Park, J.: Guided trajectory generation with diffusion models for offline model-based optimization. In: NeurIPS (2024)","DOI":"10.52202\/079017-2665"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Zhan, X., Xu, H., Zhang, Y., Zhu, X., Yin, H., Zheng, Y.: DeepThermal: combustion optimization for thermal power generating units using offline reinforcement learning. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i4.20393"},{"key":"30_CR39","unstructured":"Zoph, B., Le, Q.: Neural architecture search with reinforcement learning. In: ICLR (2017)"}],"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\/978-981-95-4091-4_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T12:29:25Z","timestamp":1787401765000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4091-4_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819540907","9789819540914"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4091-4_30","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 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"}}]}}