{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:57:41Z","timestamp":1765357061696,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030946616"},{"type":"electronic","value":"9783030946623"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-94662-3_12","type":"book-chapter","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T12:03:08Z","timestamp":1641902588000},"page":"185-205","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Signal Instructed Coordination in\u00a0Cooperative Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Liheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"issue":"1","key":"12_CR1","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/0304-4068(74)90037-8","volume":"1","author":"RJ Aumann","year":"1974","unstructured":"Aumann, R.J.: Subjectivity and correlation in randomized strategies. J. Math. Econ. 1(1), 67\u201396 (1974)","journal-title":"J. Math. Econ."},{"key":"12_CR2","unstructured":"Barber, D., Agakov, F.V.: The IM algorithm: a variational approach to information maximization. In: NIPS. p. None (2003)"},{"key":"12_CR3","unstructured":"Boutilier, C.: Sequential optimality and coordination in multiagent systems. In: IJCAI, vol. 99, pp. 478\u2013485 (1999)"},{"issue":"2","key":"12_CR4","first-page":"2008","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE SMC-Part C Appl. Rev. 38(2), 2008 (2008)","journal-title":"IEEE SMC-Part C Appl. Rev."},{"key":"12_CR5","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In: NIPS, pp. 2172\u20132180 (2016)"},{"key":"12_CR6","unstructured":"Das, A., et al.: Tarmac: Targeted multi-agent communication. arXiv preprint arXiv:1810.11187 (2018)"},{"key":"12_CR7","unstructured":"Farina, G., Ling, C.K., Fang, F., Sandholm, T.: Correlation in extensive-form games: saddle-point formulation and benchmarks. arXiv preprint arXiv:1905.12564 (2019)"},{"key":"12_CR8","unstructured":"Foerster, J.N., Assael, Y.M., de Freitas, N., Whiteson, S.: Learning to communicate to solve riddles with deep distributed recurrent Q-networks. arXiv preprint arXiv:1602.02672 (2016)"},{"key":"12_CR9","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":"12_CR10","unstructured":"Foerster, J.N., de Witt, C.A.S., Farquhar, G., Torr, P.H., Boehmer, W., Whiteson, S.: Multi-agent common knowledge reinforcement learning. arXiv preprint arXiv:1810.11702 (2018)"},{"key":"12_CR11","unstructured":"Greenwald, A., Hall, K., Serrano, R.: Correlated Q-learning. In: ICML, vol. 3, pp. 242\u2013249 (2003)"},{"key":"12_CR12","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. arXiv preprint arXiv:1810.02912 (2018)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, A.X., Leyton-Brown, K.: Polynomial-time computation of exact correlated equilibrium in compact games. In: Proceedings of the 12th ACM Conference on Electronic Commerce, pp. 119\u2013126. ACM (2011)","DOI":"10.1145\/1993574.1993593"},{"key":"12_CR14","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. In: NIPS, pp. 7254\u20137264 (2018)"},{"key":"12_CR15","unstructured":"Korkmaz, G., Kuhlman, C.J., Marathe, A., Marathe, M.V., Vega-Redondo, F.: Collective action through common knowledge using a Facebook model. In: Proceedings of the 2014 AAMAS, pp. 253\u2013260. IFAAMAS (2014)"},{"key":"12_CR16","unstructured":"Lanctot, M., et al.: A unified game-theoretic approach to multiagent reinforcement learning. In: NIPS, pp. 4190\u20134203 (2017)"},{"issue":"1","key":"12_CR17","first-page":"1","volume":"2","author":"K Leyton-Brown","year":"2008","unstructured":"Leyton-Brown, K., Shoham, Y.: Essentials of game theory: a concise multidisciplinary introduction. Synth. Lect. Artif. Intell. Mach. Learn. 2(1), 1\u201388 (2008)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"12_CR18","unstructured":"Li, Y., Song, J., Ermon, S.: Infogail: interpretable imitation learning from visual demonstrations. In: NIPS, pp. 3812\u20133822 (2017)"},{"key":"12_CR19","unstructured":"Li, Y.: Deep reinforcement learning: an overview. arXiv preprint arXiv:1701.07274 (2017)"},{"key":"12_CR20","unstructured":"Li, Y.: Deep reinforcement learning. arXiv preprint arXiv:1810.06339 (2018)"},{"key":"12_CR21","unstructured":"Lowe, R., Foerster, J., Boureau, Y.L., Pineau, J., Dauphin, Y.: On the pitfalls of measuring emergent communication. In: Proceedings of the 18th AAMAS, pp. 693\u2013701. IFAAMAS (2019)"},{"key":"12_CR22","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NIPS, pp. 6379\u20136390 (2017)"},{"issue":"1","key":"12_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0269888912000057","volume":"27","author":"L Matignon","year":"2012","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems. Knowl. Eng. Rev. 27(1), 1\u201331 (2012)","journal-title":"Knowl. Eng. Rev."},{"key":"12_CR24","unstructured":"Nunes, L., Oliveira, E.: Learning from multiple sources. In: Proceedings of the 3rd AAMAS. AAMAS 2004, pp. 1106\u20131113. IEEE Computer Society, Washington, DC, USA (2004). http:\/\/dl.acm.org\/citation.cfm?id=1018411.1018879"},{"key":"12_CR25","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":"12_CR26","unstructured":"Peng, P., et al.: Multiagent bidirectionally-coordinated nets: emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069 (2017)"},{"key":"12_CR27","unstructured":"Schneider, J.G., Wong, W.K., Moore, A.W., Riedmiller, M.A.: Distributed value functions. In: Proceedings of the 16th ICML. ICML 1999, pp. 371\u2013378. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1999). http:\/\/dl.acm.org\/citation.cfm?id=645528.657645"},{"key":"12_CR28","unstructured":"Sukhbaatar, S., Fergus, R., et al.: Learning multiagent communication with backpropagation. In: NIPS, pp. 2244\u20132252 (2016)"},{"issue":"4","key":"12_CR29","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1037\/a0037037","volume":"107","author":"KA Thomas","year":"2014","unstructured":"Thomas, K.A., DeScioli, P., Haque, O.S., Pinker, S.: The psychology of coordination and common knowledge. J. Pers. Soc. Psychol. 107(4), 657 (2014)","journal-title":"J. Pers. Soc. Psychol."},{"key":"12_CR30","unstructured":"Vinyals, O., et al.: StarCraft II: a new challenge for reinforcement learning. arXiv preprint arXiv:1708.04782 (2017)"},{"key":"12_CR31","unstructured":"Zhang, C., Lesser, V.: Coordinating multi-agent reinforcement learning with limited communication. In: Proceedings of the 2013 AAMAS, pp. 1101\u20131108. IFAAMAS (2013)"}],"container-title":["Lecture Notes in Computer Science","Distributed Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-94662-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T15:21:22Z","timestamp":1674400882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-94662-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030946616","9783030946623"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-94662-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 January 2022","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":"Shanghai","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dai22021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adai.ai\/dai\/2021\/2021.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":"31","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":"15","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":"48% - 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":"4","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)"}}]}}