{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:01:30Z","timestamp":1743026490702,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442124"},{"type":"electronic","value":"9783031442131"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44213-1_30","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"356-364","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Policies as\u00a0Multi-Agent Reinforcement Learning Strategies"],"prefix":"10.1007","author":[{"given":"Jinkun","family":"Geng","sequence":"first","affiliation":[]},{"given":"Xiubo","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"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":"30_CR1"},{"unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)","key":"30_CR2"},{"unstructured":"Chen, H., Lu, C., Ying, C., Su, H., Zhu, J.: Offline reinforcement learning via high-fidelity generative behavior modeling. arXiv preprint arXiv:2209.14548 (2022)","key":"30_CR3"},{"key":"30_CR4","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. Adv. Neural. Inf. Process. Syst. 34, 15084\u201315097 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"30_CR5","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1109\/TWC.2019.2935201","volume":"19","author":"J Cui","year":"2019","unstructured":"Cui, J., Liu, Y., Nallanathan, A.: Multi-agent reinforcement learning-based resource allocation for UAV networks. IEEE Trans. Wirel. Commun. 19(2), 729\u2013743 (2019)","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"7","key":"30_CR6","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1177\/0278364920916531","volume":"39","author":"T Fan","year":"2020","unstructured":"Fan, T., Long, P., Liu, W., Pan, J.: Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios. Int. J. Robot. Res. 39(7), 856\u2013892 (2020)","journal-title":"Int. J. Robot. Res."},{"doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","key":"30_CR7","DOI":"10.1609\/aaai.v32i1.11794"},{"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":"30_CR8"},{"key":"30_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"JK Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66\u201383. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5"},{"key":"30_CR10","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."},{"unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)","key":"30_CR11"},{"doi-asserted-by":"crossref","unstructured":"Huang, R., et al.: Fastdiff: a fast conditional diffusion model for high-quality speech synthesis. arXiv preprint arXiv:2204.09934 (2022)","key":"30_CR12","DOI":"10.24963\/ijcai.2022\/577"},{"unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961\u20132970. PMLR (2019)","key":"30_CR13"},{"unstructured":"Janner, M., Du, Y., Tenenbaum, J.B., Levine, S.: Planning with diffusion for flexible behavior synthesis. arXiv preprint arXiv:2205.09991 (2022)","key":"30_CR14"},{"unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)","key":"30_CR15"},{"key":"30_CR16","first-page":"1179","volume":"33","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 1179\u20131191 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"unstructured":"Lauer, M.: An algorithm for distributed reinforcement learning in cooperative multiagent systems. In: Proceedings of 17th International Conference on Machine Learning (2000)","key":"30_CR17"},{"unstructured":"Leibo, J.Z., Zambaldi, V., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. arXiv preprint arXiv:1702.03037 (2017)","key":"30_CR18"},{"unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)","key":"30_CR19"},{"unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"30_CR20"},{"unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)","key":"30_CR21"},{"unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)","key":"30_CR22"},{"doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)","key":"30_CR23","DOI":"10.1609\/aaai.v32i1.11492"},{"doi-asserted-by":"crossref","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 (2022)","key":"30_CR24","DOI":"10.1109\/CVPR52688.2022.01042"},{"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":"30_CR25"},{"unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)","key":"30_CR26"},{"unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, vol. 12 (1999)","key":"30_CR27"},{"issue":"4","key":"30_CR28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4), e0172395 (2017)","journal-title":"PLoS ONE"},{"unstructured":"Van Hasselt, H., Doron, Y., Strub, F., Hessel, M., Sonnerat, N., Modayil, J.: Deep reinforcement learning and the deadly triad. arXiv preprint arXiv:1812.02648 (2018)","key":"30_CR29"},{"doi-asserted-by":"crossref","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","key":"30_CR30","DOI":"10.1038\/s41586-019-1724-z"},{"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":"30_CR31"},{"key":"30_CR32","first-page":"10299","volume":"34","author":"Y Yang","year":"2021","unstructured":"Yang, Y., et al.: Believe what you see: implicit constraint approach for offline multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 10299\u201310312 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)","key":"30_CR33","DOI":"10.1109\/ICCV51070.2023.00355"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44213-1_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T15:05:50Z","timestamp":1730127950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44213-1_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442124","9783031442131"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44213-1_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","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":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","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":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted : 9 Abstract","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)"}}]}}