{"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":1750737870444,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":29,"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_15","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:41:19Z","timestamp":1750689679000},"page":"211-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Extension for\u00a0Centralized Multi-Agent Reinforcement Learning via\u00a0Online Distillation"],"prefix":"10.1007","author":[{"given":"Zeren","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangchong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoliang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"15_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR2","unstructured":"Chen, G.: A new framework for multi-agent reinforcement learning\u2013centralized training and exploration with decentralized execution via policy distillation. arXiv preprint arXiv:1910.09152 (2019)"},{"key":"15_CR3","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."},{"key":"15_CR4","unstructured":"Chen, Y., et al.: PTDE: Personalized training with distillated execution for multi-agent reinforcement learning. arXiv preprint arXiv:2210.08872 (2022)"},{"key":"15_CR5","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":"15_CR6","doi-asserted-by":"crossref","unstructured":"Guo, Q., et al.: Online knowledge distillation via collaborative learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11020\u201311029 (2020)","DOI":"10.1109\/CVPR42600.2020.01103"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Kasabov, N.: Spatio-temporal associative memories in brain-inspired spiking neural networks: Concepts and perspectives. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.23723208"},{"issue":"12","key":"15_CR8","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.3390\/bioengineering10121341","volume":"10","author":"NK Kasabov","year":"2023","unstructured":"Kasabov, N.K., Bahrami, H., Doborjeh, M., Wang, A.: Brain-inspired spatio-temporal associative memories for neuroimaging data classification: EEG and fMRI. Bioengineering 10(12), 1341 (2023)","journal-title":"Bioengineering"},{"key":"15_CR9","unstructured":"Kuba, J.G., et al.: Trust region policy optimisation in multi-agent reinforcement learning. arXiv preprint arXiv:2109.11251 (2021)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Machine learning proceedings 1994, pp. 157\u2013163. Elsevier (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"15_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":"15_CR12","unstructured":"Meng, L., et al.: Offline pre-trained multi-agent decision transformer: one big sequence model tackles all smac tasks. arXiv preprint arXiv:2112.02845 (2021)"},{"issue":"10","key":"15_CR13","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1109\/JSAC.2019.2933973","volume":"37","author":"YS Nasir","year":"2019","unstructured":"Nasir, Y.S., Guo, D.: Multi-agent deep reinforcement learning for dynamic power allocation in wireless networks. IEEE J. Sel. Areas Commun. 37(10), 2239\u20132250 (2019)","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"15_CR14","unstructured":"Omidshafiei, S., Pazis, J., Amato, C., How, J.P., Vian, J.: Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: International Conference on Machine Learning, pp. 2681\u20132690. PMLR (2017)"},{"key":"15_CR15","unstructured":"Rashid, T., Samvelyan, M., Witt, C.S.D., Farquhar, G., Foerster, J.N., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning. ArXiv:abs\/1803.11485 (2018). https:\/\/api.semanticscholar.org\/CorpusID:4533648"},{"key":"15_CR16","doi-asserted-by":"publisher","unstructured":"Ren, Y., Zhong, Z., Shi, X., Zhu, Y., Yuan, C., Li, M.: Tailoring instructions to student\u2019s learning levels boosts knowledge distillation. In: Rogers, A., Boyd-Graber, J.L., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 1990\u20132006. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.111","DOI":"10.18653\/V1\/2023.ACL-LONG.111"},{"key":"15_CR17","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"key":"15_CR18","unstructured":"Shi, W., Song, Y., Zhou, H., Li, B., Li, L.: Learning from deep model via exploring local targets (2020)"},{"key":"15_CR19","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"15_CR20","unstructured":"Sunehag, P., et\u00a0al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"issue":"4","key":"15_CR21","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"},{"key":"15_CR22","first-page":"226","volume":"35","author":"WC Tseng","year":"2022","unstructured":"Tseng, W.C., Wang, T., Lin, Y.C., Isola, P.: Offline multi-agent reinforcement learning with knowledge distillation. Adv. Neural. Inf. Process. Syst. 35, 226\u2013237 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"7782","key":"15_CR24","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"15_CR25","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":"15_CR26","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":"15_CR27","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":"15_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Cityflow: A multi-agent reinforcement learning environment for large scale city traffic scenario. In: The World Wide Web Conference, pp. 3620\u20133624 (2019)","DOI":"10.1145\/3308558.3314139"},{"key":"15_CR29","unstructured":"Zhao, J., Hu, X., Yang, M., Zhou, W., Zhu, J., Li, H.: Ctds: Centralized teacher with decentralized student for multi-agent reinforcement learning. IEEE Transactions on Games (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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:41:25Z","timestamp":1750689685000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6582-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665815","9789819665822"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6582-2_15","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":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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"}}]}}