{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:58:38Z","timestamp":1775325518234,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031255489","type":"print"},{"value":"9783031255496","type":"electronic"}],"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\/978-3-031-25549-6_5","type":"book-chapter","created":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T09:07:44Z","timestamp":1679389664000},"page":"60-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimistic Exploration Based on\u00a0Categorical-DQN for\u00a0Cooperative Markov Games"],"prefix":"10.1007","author":[{"given":"Yu","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9157-6050","authenticated-orcid":false,"given":"Chengwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kangjie","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanqing","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xintian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,22]]},"reference":[{"key":"5_CR1","unstructured":"Azar, M.G., Munos, R., Kappen, B.: On the sample complexity of reinforcement learning with a generative model. In: Proceedings of the 29th International Conference on Machine Learning, ICML 2012 (2012)"},{"key":"5_CR2","unstructured":"Barth-Maron, G., et al.: Distributed distributional deterministic policy gradients. In: 6th International Conference on Learning Representations, ICLR 2018 (2018)"},{"key":"5_CR3","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017 (2017)"},{"issue":"1","key":"5_CR4","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2013","unstructured":"Cao, Y., Yu, W., Ren, W., Chen, G.: An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans. Industr. Inform. 9(1), 427\u2013438 (2013)","journal-title":"IEEE Trans. Industr. Inform."},{"key":"5_CR5","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","unstructured":"Chu, T., Wang, J., Codec\u00e0, L., Li, Z.: Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans. Intell. Transp. Syst. 21, 1086\u20131095 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. arXiv preprint arXiv:1806.06923 (2018)","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Dabney, W., Rowland, M., Bellemare, M.G., Munos, R.: Distributional reinforcement learning with quantile regression. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, AAAI 2018) (2018)","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"5_CR9","unstructured":"Hao, X., Wang, W., Hao, J., Yang, Y.: Independent generative adversarial self-imitation learning in cooperative multiagent systems. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2019 (2019)"},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1007\/978-3-642-34106-9_26","volume-title":"Algorithmic Learning Theory","author":"T Lattimore","year":"2012","unstructured":"Lattimore, T., Hutter, M.: PAC bounds for discounted MDPs. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds.) ALT 2012. LNCS (LNAI), vol. 7568, pp. 320\u2013334. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-34106-9_26"},{"key":"5_CR11","unstructured":"Lauer, M., Riedmiller, M.A.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proceedings of the 17h International Conference on Machine Learning, pp. 535\u2013542 (2000)"},{"key":"5_CR12","unstructured":"Lowe, R., WU, Y., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30, pp. 6379\u20136390. Curran Associates, Inc. (2017)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Fort-Piat, N.L.: Hysteretic Q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems IROS, pp. 64\u201369. IEEE (2007)","DOI":"10.1109\/IROS.2007.4399095"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Matignon, L., Laurent, G.J., Le Fort Piat, N.: Review: independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems. Knowl. Eng. Rev. 27(1), 1\u201331 (2012)","DOI":"10.1017\/S0269888912000057"},{"key":"5_CR15","unstructured":"Mavrin, B., Yao, H., Kong, L., Wu, K., Yu, Y.: Distributional reinforcement learning for efficient exploration. In: International Conference on Machine Learning, pp. 4424\u20134434 (2019)"},{"issue":"2","key":"5_CR16","doi-asserted-by":"publisher","first-page":"429","DOI":"10.2307\/1428011","volume":"29","author":"A M\u00fcller","year":"1997","unstructured":"M\u00fcller, A.: Integral probability metrics and their generating classes of functions. Adv. Appl. Probab. 29(2), 429\u2013443 (1997)","journal-title":"Adv. Appl. Probab."},{"key":"5_CR17","unstructured":"Omidshafiei, S., Pazis, J., Amato, C., How, J.P., Vian, J.: Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2681\u20132690. JMLR. org (2017)"},{"key":"5_CR18","unstructured":"Palmer, G., Savani, R., Tuyls, K.: Negative update intervals in deep multi-agent reinforcement learning. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (2019)"},{"key":"5_CR19","unstructured":"Palmer, G., Tuyls, K., Bloembergen, D., Savani, R.: Lenient multi-agent deep reinforcement learning. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (2018)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Panait, L., Sullivan, K., Luke, S.: Lenient learners in cooperative multiagent systems. In: Proceedings of the 5th International Joint conference on Autonomous Agents and Multiagent Systems (2006)","DOI":"10.1145\/1160633.1160776"},{"key":"5_CR21","unstructured":"Rashid, T., Samvelyan, M., Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4292\u20134301 (2018)"},{"key":"5_CR22","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D., Yi, Y.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019 (2019)"},{"issue":"8","key":"5_CR23","doi-asserted-by":"publisher","first-page":"7426","DOI":"10.1109\/TVT.2021.3090796","volume":"70","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Jin, S., Xue, W., Xie, X., Chen, S., Chen, R.: Independent reinforcement learning for weakly cooperative multiagent traffic control problem. IEEE Trans. Veh. Technol. 70(8), 7426\u20137436 (2021)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Neighborhood cooperative multiagent reinforcement learning for adaptive traffic signal control in epidemic regions. IEEE Trans. Intell. Transp. Syst. 1\u201312 (2022)","DOI":"10.1109\/TITS.2022.3173490"}],"container-title":["Lecture Notes in Computer Science","Distributed Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25549-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T09:08:46Z","timestamp":1679389726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25549-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031255489","9783031255496"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25549-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Distributed Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dai22022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adai.ai\/dai\/2022\/2022.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","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":"5","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":"0","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":"31% - 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":"3","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}