{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:38:23Z","timestamp":1782833903117,"version":"3.54.5"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729829","type":"print"},{"value":"9783031729836","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72983-6_1","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Diffusion Models as\u00a0Optimizers for\u00a0Efficient Planning in\u00a0Offline RL"],"prefix":"10.1007","author":[{"given":"Renming","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunqiang","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengtao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"1_CR1","unstructured":"Agrawal, P., Nair, A.V., Abbeel, P., Malik, J., Levine, S.: Learning to poke by poking: experiential learning of intuitive physics. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"1_CR2","unstructured":"Ajay, A., Du, Y., Gupta, A., Tenenbaum, J., Jaakkola, T., Agrawal, P.: Is conditional generative modeling all you need for decision-making? arXiv preprint arXiv:2211.15657 (2022)"},{"key":"1_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"1_CR4","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. In: Advances in Neural Information Processing Systems, vol. 34, pp. 15084\u201315097 (2021)"},{"key":"1_CR5","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"1_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR7","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"1_CR8","unstructured":"Du, Y., Mordatch, I.: Implicit generation and generalization in energy-based models. arXiv preprint arXiv:1903.08689 (2019)"},{"key":"1_CR9","unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4RL: datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 (2020)"},{"key":"1_CR10","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":"1_CR11","unstructured":"Furuta, H., Matsuo, Y., Gu, S.S.: Generalized decision transformer for offline hindsight information matching. arXiv preprint arXiv:2111.10364 (2021)"},{"key":"1_CR12","unstructured":"Grathwohl, W., Wang, K.C., Jacobsen, J.H., Duvenaud, D., Zemel, R.: Learning the stein discrepancy for training and evaluating energy-based models without sampling. In: International Conference on Machine Learning, pp. 3732\u20133747. PMLR (2020)"},{"key":"1_CR13","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"1_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"1_CR17","unstructured":"Janner, M., Du, Y., Tenenbaum, J.B., Levine, S.: Planning with diffusion for flexible behavior synthesis. arXiv preprint arXiv:2205.09991 (2022)"},{"key":"1_CR18","unstructured":"Janner, M., Li, Q., Levine, S.: Offline reinforcement learning as one big sequence modeling problem. In: Advances in Neural Information Processing Systems, vol. 34, pp. 1273\u20131286 (2021)"},{"key":"1_CR19","unstructured":"Kidambi, R., Rajeswaran, A., Netrapalli, P., Joachims, T.: Morel: model-based offline reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21810\u201321823 (2020)"},{"key":"1_CR20","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":"1_CR21","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1179\u20131191 (2020)"},{"key":"1_CR22","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":"1_CR23","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":"1_CR24","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7559\u20137566. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"1_CR25","unstructured":"Ni, F., et al.: MetaDiffuser: diffusion model as conditional planner for offline meta-rl. arXiv preprint arXiv:2305.19923 (2023)"},{"key":"1_CR26","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"1_CR27","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"1_CR28","unstructured":"Nijkamp, E., Hill, M., Zhu, S.C., Wu, Y.N.: Learning non-convergent non-persistent short-run MCMC toward energy-based model. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Pathak, D., et al.: Zero-shot visual imitation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2050\u20132053 (2018)","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"1_CR30","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley (2014)"},{"key":"1_CR31","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"issue":"8","key":"1_CR32","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"1_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"1_CR34","unstructured":"Ritter, S., Faulkner, R., Sartran, L., Santoro, A., Botvinick, M., Raposo, D.: Rapid task-solving in novel environments. arXiv preprint arXiv:2006.03662 (2020)"},{"key":"1_CR35","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"1_CR36","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"1_CR37","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"1_CR38","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"1_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR40","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":"1_CR41","unstructured":"Wu, Y., Tucker, G., Nachum, O.: Behavior regularized offline reinforcement learning. arXiv preprint arXiv:1911.11361 (2019)"},{"key":"1_CR42","unstructured":"Zambaldi, V., et\u00a0al.: Deep reinforcement learning with relational inductive biases. In: International Conference on Learning Representations (2018)"},{"key":"1_CR43","unstructured":"Zhang, Q., et al.: Saformer: a conditional sequence modeling approach to offline safe reinforcement learning. arXiv preprint arXiv:2301.12203 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72983-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:52:48Z","timestamp":1730109168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72983-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031729829","9783031729836"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72983-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}