{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T08:11:59Z","timestamp":1768551119316,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819980819","type":"print"},{"value":"9789819980826","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8082-6_28","type":"book-chapter","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T16:08:09Z","timestamp":1699978089000},"page":"358-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Action Prediction for\u00a0Cooperative Exploration in\u00a0Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yanqiang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"key":"28_CR1","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"28_CR2","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-642-14435-6_7","volume-title":"Innovations in Multi-agent Systems and Applications-1","author":"L Bu\u015foniu","year":"2010","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., De Schutter, B.: Multi-agent reinforcement learning: an overview. In: Srinivasan, D., Jain, L.C. (eds.) Innovations in Multi-agent Systems and Applications-1, pp. 183\u2013221. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-14435-6_7"},{"issue":"11","key":"28_CR3","doi-asserted-by":"publisher","first-page":"3409","DOI":"10.1109\/TNNLS.2019.2891792","volume":"30","author":"N Dilokthanakul","year":"2019","unstructured":"Dilokthanakul, N., Kaplanis, C., Pawlowski, N., Shanahan, M.: Feature control as intrinsic motivation for hierarchical reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3409\u20133418 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"28_CR4","unstructured":"Du, Y., Han, L., Fang, M., Liu, J., Dai, T., Tao, D.: LIIR: learning individual intrinsic reward in multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"28_CR5","unstructured":"Goyal, A., et al.: Infobot: transfer and exploration via the information bottleneck. arXiv preprint arXiv:1901.10902 (2019)"},{"key":"28_CR6","unstructured":"Graves, A.: Practical variational inference for neural networks. In: Advances in Neural Information Processing Systems, vol. 24 (2011)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Hao, J., et al.: Exploration in deep reinforcement learning: from single-agent to multiagent domain. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"28_CR8","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 (2021)"},{"key":"28_CR9","unstructured":"Jaques, N., et al.: Social influence as intrinsic motivation for multi-agent deep reinforcement learning. In: International Conference on Machine Learning, pp. 3040\u20133049. PMLR (2019)"},{"issue":"10","key":"28_CR10","doi-asserted-by":"publisher","first-page":"2282","DOI":"10.1109\/JSAC.2019.2933962","volume":"37","author":"L Liang","year":"2019","unstructured":"Liang, L., Ye, H., Li, G.Y.: Spectrum sharing in vehicular networks based on multi-agent reinforcement learning. IEEE J. Sel. Areas Commun. 37(10), 2282\u20132292 (2019)","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"28_CR11","unstructured":"Lowe, R., Wu, Y.I., 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 (2017)"},{"key":"28_CR12","unstructured":"Mahajan, A., Rashid, T., Samvelyan, M., Whiteson, S.: Maven: multi-agent variational exploration. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"28_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A Concise Introduction to Decentralized POMDPs. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8"},{"key":"28_CR14","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1613\/jair.2447","volume":"32","author":"FA Oliehoek","year":"2008","unstructured":"Oliehoek, F.A., Spaan, M.T., Vlassis, N.: Optimal and approximate Q-value functions for decentralized POMDPs. J. Artif. Intell. Res. 32, 289\u2013353 (2008)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Oroojlooy, A., Hajinezhad, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 1\u201346 (2022)","DOI":"10.1007\/s10489-022-04105-y"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"28_CR17","first-page":"10199","volume":"33","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Farquhar, G., Peng, B., Whiteson, S.: Weighted QMIX: expanding monotonic value function factorisation for deep multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 10199\u201310210 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR18","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":"28_CR19","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"key":"28_CR20","unstructured":"Shalev-Shwartz, S., Shammah, S., Shashua, A.: Safe, multi-agent, reinforcement learning for autonomous driving. arXiv preprint arXiv:1610.03295 (2016)"},{"key":"28_CR21","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":"28_CR22","doi-asserted-by":"crossref","unstructured":"Su, J., Adams, S., Beling, P.: Value-decomposition multi-agent actor-critics. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11352\u201311360 (2021)","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"28_CR23","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"28_CR24","unstructured":"Tang, H., et al.: # exploration: a study of count-based exploration for deep reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"28_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":"28_CR26","unstructured":"Wang, T., Gupta, T., Peng, B., Mahajan, A., Whiteson, S., Zhang, C.: Rode: learning roles to decompose multi-agent tasks. In: Proceedings of the International Conference on Learning Representations. OpenReview (2021)"},{"key":"28_CR27","unstructured":"Wang, T., Wang, J., Wu, Y., Zhang, C.: Influence-based multi-agent exploration. arXiv preprint arXiv:1910.05512 (2019)"},{"key":"28_CR28","unstructured":"Wang, Y., Han, B., Wang, T., Dong, H., Zhang, C.: Off-policy multi-agent decomposed policy gradients. arXiv preprint arXiv:2007.12322 (2020)"},{"key":"28_CR29","first-page":"11853","volume":"33","author":"M Zhou","year":"2020","unstructured":"Zhou, M., Liu, Z., Sui, P., Li, Y., Chung, Y.Y.: Learning implicit credit assignment for cooperative multi-agent reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 11853\u201311864 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8082-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:31:24Z","timestamp":1710354684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8082-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"ISBN":["9789819980819","9789819980826"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8082-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,15]]},"assertion":[{"value":"15 November 2023","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":"Changsha","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}