{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T18:40:25Z","timestamp":1743619225441,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819642069","type":"print"},{"value":"9789819642076","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\/978-981-96-4207-6_31","type":"book-chapter","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T18:27:07Z","timestamp":1743618427000},"page":"339-351","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multiagent Reinforcement Learning Based on\u00a0Structural Coordination"],"prefix":"10.1007","author":[{"given":"Yixuan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junlan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Chau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Agogino, A., Turner, K.: Multi-agent reward analysis for learning in noisy domains. In: Proceedings of the Fourth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 81\u201388 (2005)","DOI":"10.1145\/1082473.1082486"},{"key":"31_CR2","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10458-004-6975-9","volume":"10","author":"AL Bazzan","year":"2005","unstructured":"Bazzan, A.L.: A distributed approach for coordination of traffic signal agents. Auton. Agent. Multi-Agent Syst. 10, 131\u2013164 (2005)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"31_CR3","unstructured":"Boutilier, C.: Sequential optimality and coordination in multiagent systems. In: IJCAI, vol.\u00a099, pp. 478\u2013485 (1999)"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Chalkiadakis, G., Boutilier, C.: Coordination in multiagent reinforcement learning: a Bayesian approach. In: Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 709\u2013716 (2003)","DOI":"10.1145\/860575.860689"},{"key":"31_CR5","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. AAAI\/IAAI 1998(746\u2013752), 2 (1998)"},{"key":"31_CR6","unstructured":"Devlin, S., Yliniemi, L., Kudenko, D., Tumer, K.: Potential-based difference rewards for multiagent reinforcement learning. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, pp. 165\u2013172 (2014)"},{"key":"31_CR7","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1613\/jair.5565","volume":"61","author":"F Fioretto","year":"2018","unstructured":"Fioretto, F., Pontelli, E., Yeoh, W.: Distributed constraint optimization problems and applications: A survey. J. Artif. Intell. Res. 61, 623\u2013698 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"31_CR8","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":"31_CR9","unstructured":"Han, D., Lu, C.X., Michalak, T., Wooldridge, M.: Multiagent model-based credit assignment for continuous control. In: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, pp. 571\u2013579 (2022)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Shapley counterfactual credits for multi-agent reinforcement learning. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 934\u2013942 (2021)","DOI":"10.1145\/3447548.3467420"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Tinka, A., Kiesel, S., Durham, J.W., Kumar, T.S., Koenig, S.: Lifelong multi-agent path finding in large-scale warehouses. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 11272\u201311281 (2021)","DOI":"10.1609\/aaai.v35i13.17344"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., Richards, A., Sooriyabandara, M.: Asynchronous reliability-aware multi-uav coverage path planning. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 10023\u201310029. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9560770"},{"key":"31_CR13","unstructured":"Li, S., Gupta, J.K., Morales, P., Allen, R., Kochenderfer, M.J.: Deep implicit coordination graphs for multi-agent reinforcement learning. arXiv preprint arXiv:2006.11438 (2020)"},{"issue":"178","key":"31_CR14","first-page":"1","volume":"24","author":"W Li","year":"2023","unstructured":"Li, W., Jin, B., Wang, X., Yan, J., Zha, H.: F2A2: flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning. J. Mach. Learn. Res. 24(178), 1\u201375 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"31_CR15","unstructured":"Liu, S., et al.: Adaptive value decomposition with greedy marginal contribution computation for cooperative multi-agent reinforcement learning. In: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, pp. 31\u201339 (2023)"},{"key":"31_CR16","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Le\u00a0Fort-Piat, N.: Hysteretic Q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: 2007 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 64\u201369. IEEE (2007)","DOI":"10.1109\/IROS.2007.4399095"},{"issue":"178","key":"31_CR18","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(178), 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"31_CR19","first-page":"5","volume":"41","author":"S Smith","year":"2020","unstructured":"Smith, S.: Smart infrastructure for future urban mobility. AI Mag. 41(1), 5\u201318 (2020)","journal-title":"AI Mag."},{"key":"31_CR20","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":"31_CR21","unstructured":"Sunehag, P., et\u00a0al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, pp. 2085\u20132087 (2018)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"31_CR23","unstructured":"Troullinos, D., Chalkiadakis, G., Papamichail, I., Papageorgiou, M.: Collaborative multiagent decision making for lane-free autonomous driving. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1335\u20131343 (2021)"},{"key":"31_CR24","unstructured":"Wang, J., Zhang, Y., Gu, Y., Kim, T.K.: Shaq: Incorporating shapley value theory into multi-agent q-learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 5941\u20135954 (2022)"},{"key":"31_CR25","unstructured":"Wang, T., Zeng, L., Dong, W., Yang, Q., Yu, Y., Zhang, C.: Context-aware sparse deep coordination graphs. arXiv preprint arXiv:2106.02886 (2021)"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Lyu, X., Amato, C.: Local advantage actor-critic for robust multi-agent deep reinforcement learning. In: 2021 International Symposium on Multi-robot and Multi-agent Systems (MRS), pp. 155\u2013163. IEEE (2021)","DOI":"10.1109\/MRS50823.2021.9620607"},{"issue":"2","key":"31_CR27","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1109\/TITS.2019.2893683","volume":"21","author":"C Yu","year":"2019","unstructured":"Yu, C., et al.: Distributed multiagent coordinated learning for autonomous driving in highways based on dynamic coordination graphs. IEEE Trans. Intell. Transp. Syst. 21(2), 735\u2013748 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"31_CR28","unstructured":"Zhou, M., Liu, Z., Sui, P., Li, Y., Chung, Y.Y.: Learning implicit credit assignment for cooperative multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 11853\u201311864 (2020)"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Computing, Applications and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-4207-6_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T18:27:19Z","timestamp":1743618439000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-4207-6_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819642069","9789819642076"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-4207-6_31","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":"1 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PDCAT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel and Distributed Computing: Applications and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"14 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pdcat2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/hpcc.siat.ac.cn\/meeting\/pdcat2024\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}