{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T04:04:30Z","timestamp":1750737870010,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665815","type":"print"},{"value":"9789819665822","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-6582-2_14","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:40:32Z","timestamp":1750689632000},"page":"198-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MA-Mamba: Multi-Agent Reinforcement Learning with\u00a0State Space Model"],"prefix":"10.1007","author":[{"given":"Yuan","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-802X","authenticated-orcid":false,"given":"Jian","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0176-3088","authenticated-orcid":false,"given":"Ke","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"14_CR1","unstructured":"Dai, Y., et al.: Is mamba compatible with trajectory optimization in offline reinforcement learning? arXiv preprint arXiv:2405.12094 (2024)"},{"key":"14_CR2","unstructured":"Deng, F., Park, J., Ahn, S.: Facing off world model backbones: RNNs, transformers, and s4. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Deng, X., Li, N., Mguni, D., Wang, J., Yang, Y.: On the complexity of computing markov perfect equilibrium in general-sum stochastic games. National Sci. Rev. 10, nwac256 (2023)","DOI":"10.1093\/nsr\/nwad024"},{"key":"14_CR4","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.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"14_CR5","unstructured":"Grudzien\u00a0Kuba, J., Feng, X., Ding, S., Dong, H., Wang, J., Yang, Y.: Heterogeneous-agent mirror learning: a continuum of solutions to cooperative marl. arXiv e-prints pp. arXiv\u20132208 (2022)"},{"key":"14_CR6","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"14_CR7","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"14_CR8","unstructured":"Kuba, J.G., et al.: Trust region policy optimisation in multi-agent reinforcement learning. arXiv preprint arXiv:2109.11251 (2021)"},{"key":"14_CR9","first-page":"13458","volume":"34","author":"JG Kuba","year":"2021","unstructured":"Kuba, J.G., et al.: Settling the variance of multi-agent policy gradients. Adv. Neural. Inf. Process. Syst. 34, 13458\u201313470 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR10","unstructured":"Liu, J., et al.: Maximum entropy heterogeneous-agent reinforcement learning. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"14_CR11","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"14_CR12","unstructured":"Lu, C., et al.: Structured state space models for in-context reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Amato, C., et\u00a0al.: A concise introduction to decentralized POMDPs, vol.\u00a01. Springer (2016)","DOI":"10.1007\/978-3-319-28929-8_1"},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy, A., Hajinezhad, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 53, 13677\u201313722 (2023)","journal-title":"Appl. Intell."},{"key":"14_CR15","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21, 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR16","unstructured":"Samsami, M.R., Zholus, A., Rajendran, J., Chandar, S.: Mastering memory tasks with world models. arXiv preprint arXiv:2403.04253 (2024)"},{"key":"14_CR17","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. Pmlr (2014)"},{"key":"14_CR18","unstructured":"Sunehag, P., et\u00a0al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"14_CR19","first-page":"16509","volume":"35","author":"M Wen","year":"2022","unstructured":"Wen, M., et al.: Multi-agent reinforcement learning is a sequence modeling problem. Adv. Neural. Inf. Process. Syst. 35, 16509\u201316521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR20","unstructured":"Yang, Y., et al.: Multi-agent determinantal q-learning. In: International Conference on Machine Learning, pp. 10757\u201310766. PMLR (2020)"},{"key":"14_CR21","unstructured":"Yu, C., et al.: The surprising effectiveness of ppo in cooperative multi-agent games. In: Advances in Neural Information Processing Systems, pp. 24611\u201324624 (2022)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6582-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:40:38Z","timestamp":1750689638000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6582-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665815","9789819665822"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6582-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 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":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}