{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:14:39Z","timestamp":1743077679806,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819997848"},{"type":"electronic","value":"9789819997855"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-9785-5_31","type":"book-chapter","created":{"date-parts":[[2024,2,3]],"date-time":"2024-02-03T18:02:05Z","timestamp":1706983325000},"page":"446-455","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decision Poisson: From Universal Gravitation to\u00a0Offline Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Heqiu","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhicong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanghua","family":"Mo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dixuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,4]]},"reference":[{"key":"31_CR1","unstructured":"Agarwal, R., Schuurmans, D., Norouzi, M.: An optimistic perspective on offline reinforcement learning. In: International Conference on Machine Learning, pp. 104\u2013114. PMLR"},{"key":"31_CR2","unstructured":"Ajay, A., Du, Y., Gupta, A., Tenenbaum, J., Jaakkola, T., Agrawal, P.: Is conditional generative modeling all you need for decision-making?"},{"key":"31_CR3","unstructured":"Chen, L., et al.: Decision transformer: Reinforcement learning via sequence modeling. 34, pp. 15084\u201315097"},{"key":"31_CR4","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. Advances in neural information processing systems, 31 (2018)"},{"key":"31_CR5","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. 34, pp. 8780\u20138794"},{"key":"31_CR6","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4rl: datasets for deep data-driven reinforcement learning"},{"key":"31_CR7","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062. PMLR (2019)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Giuliari, F., Hasan, I., Cristani, M., Galasso, F.: Transformer networks for trajectory forecasting. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10335\u201310342. IEEE","DOI":"10.1109\/ICPR48806.2021.9412190"},{"key":"31_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. 33, 6840\u20136851"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Diffusion-based generation, optimization, and planning in 3d scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16750\u201316761","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"31_CR11","unstructured":"Janner, M., Du, Y., Tenenbaum, J.B., Levine, S.: Planning with diffusion for flexible behavior synthesis"},{"key":"31_CR12","first-page":"21810","volume":"33","author":"R Kidambi","year":"2020","unstructured":"Kidambi, R., Rajeswaran, A., Netrapalli, P., Joachims, T.: Morel: model-based offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 21810\u201321823 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR13","unstructured":"Kostrikov, I., Nair, A., Levine, S.: Offline reinforcement learning with implicit q-learning"},{"key":"31_CR14","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. 33, pp. 1179\u20131191"},{"key":"31_CR15","unstructured":"Laroche, R., Trichelair, P., Des Combes, R.T.: Safe policy improvement with baseline bootstrapping. In International conference on machine learning, pp. 3652\u20133661. PMLR (2019)"},{"key":"31_CR16","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers"},{"key":"31_CR17","unstructured":"Prudencio, R.F., ROA Maximo, M., Colombini, E.L.: A survey on offline reinforcement learning: Taxonomy, review, and open problems. IEEE"},{"key":"31_CR18","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695"},{"key":"31_CR19","unstructured":"Sun, Y., et al.: Retentive network: a successor to transformer for large language models"},{"key":"31_CR20","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT press (2018)"},{"issue":"3","key":"31_CR21","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G., et al.: Temporal difference learning and td-gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"key":"31_CR22","unstructured":"Xu, Y., Liu, Z., Tegmark, M., Jaakkola, T.: Poisson flow generative models. 35, pp. 16782\u201316795"},{"key":"31_CR23","unstructured":"Yang, L., et al.: Diffusion models: a comprehensive survey of methods and applications"},{"key":"31_CR24","unstructured":"Yang, S., Nachum, O., Du, Y., Wei, J., Abbeel, P., Schuurmans, D.: Foundation models for decision making: Problems, methods, and opportunities"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Zhong, Z., et al.: Guided conditional diffusion for controllable traffic simulation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 3560\u20133566. IEEE","DOI":"10.1109\/ICRA48891.2023.10161463"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence Security and Privacy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-9785-5_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T02:08:38Z","timestamp":1731204518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-9785-5_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819997848","9789819997855"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-9785-5_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"4 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIS&P","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence Security and Privacy","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ais&p2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/aisp2023","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"115","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23 large model and security workshop papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}