{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T16:49:50Z","timestamp":1758041390127,"version":"3.44.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032045577"},{"type":"electronic","value":"9783032045584"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"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\/978-3-032-04558-4_24","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:17:13Z","timestamp":1757589433000},"page":"298-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Stability of\u00a0Parameter Sharing in\u00a0Cooperative Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yurui","family":"Li","sequence":"first","affiliation":[]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shijian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"24_CR1","first-page":"10707","volume":"33","author":"F Christianos","year":"2020","unstructured":"Christianos, F., Sch\u00e4fer, L., Albrecht, S.: Shared experience actor-critic for multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 10707\u201310717 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR2","unstructured":"Hu, J., Jiang, S., Harding, S.A., Wu, H., Liao, S.W.: Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning. arXiv e-prints pp. arXiv-2102 (2021)"},{"key":"24_CR3","unstructured":"H\u00fcttenrauch, M., \u0160o\u0161i\u0107, A., Neumann, G.: Guided deep reinforcement learning for swarm systems. arXiv preprint arXiv:1709.06011 (2017)"},{"key":"24_CR4","unstructured":"Jiang, J., Lu, Z.: The emergence of individuality. In: International Conference on Machine Learning, pp. 4992\u20135001. PMLR (2021)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Kurach, K., et al.: Google research football: a novel reinforcement learning environment. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 4501\u20134510 (2020)","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"24_CR6","first-page":"3991","volume":"34","author":"C Li","year":"2021","unstructured":"Li, C., Wang, T., Wu, C., Zhao, Q., Yang, J., Zhang, C.: Celebrating diversity in shared multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 3991\u20134002 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"McLachlan, G.J., Basford, K.E.: Mixture models: inference and applications to clustering, vol.\u00a038. M. Dekker New York (1988)","DOI":"10.2307\/2348072"},{"key":"24_CR8","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1146\/annurev-statistics-031017-100325","volume":"6","author":"GJ McLachlan","year":"2019","unstructured":"McLachlan, G.J., Lee, S.X., Rathnayake, S.I.: Finite mixture models. Ann. Rev. Stat. Appl. 6, 355\u2013378 (2019)","journal-title":"Ann. Rev. Stat. Appl."},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Amato, C.: A concise introduction to decentralized POMDPs. Springer (2016)","DOI":"10.1007\/978-3-319-28929-8"},{"key":"24_CR10","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"24_CR11","unstructured":"Singh, A.J., Kumar, A., Lau, H.C.: Hierarchical multiagent reinforcement learning for maritime traffic management (2020)"},{"key":"24_CR12","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"24_CR13","first-page":"15032","volume":"34","author":"J Terry","year":"2021","unstructured":"Terry, J., et al.: Pettingzoo: gym for multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 34, 15032\u201315043 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR14","unstructured":"Wang, J., Ren, Z., Liu, T., Yu, Y., Zhang, C.: Qplex: duplex dueling multi-agent q-learning. arXiv preprint arXiv:2008.01062 (2020)"},{"key":"24_CR15","unstructured":"Wang, T., Dong, H., Lesser, V., Zhang, C.: Roma: multi-agent reinforcement learning with emergent roles. arXiv preprint arXiv:2003.08039 (2020)"},{"key":"24_CR16","unstructured":"Wang, T., Gupta, T., Mahajan, A., Peng, B., Whiteson, S., Zhang, C.: Rode: learning roles to decompose multi-agent tasks. arXiv preprint arXiv:2010.01523 (2020)"},{"key":"24_CR17","unstructured":"Yang, Y., et al.: Qatten: a general framework for cooperative multiagent reinforcement learning. arXiv preprint arXiv:2002.03939 (2020)"},{"key":"24_CR18","first-page":"24611","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu, C., et al.: The surprising effectiveness of PPO in cooperative multi-agent games. Adv. Neural. Inf. Process. Syst. 35, 24611\u201324624 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR19","unstructured":"Zang, Y., et al.: Automatic grouping for efficient cooperative multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"24_CR20","unstructured":"Zhou, M., et al.: Smarts: scalable multi-agent reinforcement learning training school for autonomous driving. arXiv preprint arXiv:2010.09776 (2020)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04558-4_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:17:19Z","timestamp":1757589439000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04558-4_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045577","9783032045584"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04558-4_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","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":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}