{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T12:07:29Z","timestamp":1771070849002,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032175410","type":"print"},{"value":"9783032175427","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-17542-7_3","type":"book-chapter","created":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T11:21:49Z","timestamp":1771068109000},"page":"38-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Utility and\u00a0Implementation of\u00a0Explicit Commands for\u00a0Ad-Hoc Coordination"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1601-6253","authenticated-orcid":false,"given":"Timothy","family":"Flavin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6107-4095","authenticated-orcid":false,"given":"Sandip","family":"Sen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,15]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Agmon, N., Barrett, S., Stone, P.: Modeling uncertainty in leading ad hoc teams. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-Agent Systems, pp. 397\u2013404 (2014)","DOI":"10.65109\/TEFP6433"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Agmon, N., Stone, P.: Leading ad hoc agents in joint action settings with multiple teammates. In: AAMAS, pp. 341\u2013348 (2012)","DOI":"10.65109\/PKLD6426"},{"issue":"2","key":"3_CR3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"3_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2019.103216","volume":"280","author":"N Bard","year":"2020","unstructured":"Bard, N., et al.: The hanabi challenge: a new frontier for ai research. Artif. Intell. 280, 103216 (2020)","journal-title":"Artif. Intell."},{"issue":"4","key":"3_CR5","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002)","journal-title":"Math. Oper. Res."},{"key":"3_CR6","unstructured":"Berry, D.A., Fristedt, B.: Bandit problems: sequential allocation of experiments (monographs on statistics and applied probability). London: Chapman Hall 5(71-87), 7 (1985)"},{"key":"3_CR7","unstructured":"Besbes, O., Gur, Y., Zeevi, A.: Stochastic multi-armed-bandit problem with non-stationary rewards. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"3_CR8","unstructured":"Carroll, M., et al.: On the utility of learning about humans for human-ai coordination. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Crawford, V.P., Sobel, J.: Strategic information transmission. Econometrica J. Econometric Soc. 1431\u20131451 (1982)","DOI":"10.2307\/1913390"},{"key":"3_CR10","unstructured":"Cui, B., Hu, H., Lupu, A., Sokota, S., Foerster, J.: Off-team learning. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 15407\u201315419. Curran Associates, Inc. (2022)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Da\u00a0Silva, F.L., Glatt, R., Costa, A.H.R.: Simultaneously learning and advising in multiagent reinforcement learning. In: Proceedings of the 16th Conference on Autonomous Agents and Multiagent Systems, pp. 1100\u20131108 (2017)","DOI":"10.65109\/VNGH9212"},{"key":"3_CR12","unstructured":"Foerster, J., Assael, I.A., De\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"issue":"1","key":"3_CR13","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR14","unstructured":"Gessler, T., Dizdarevic, T., Calinescu, A., Ellis, B., Lupu, A., Foerster, J.N.: Overcookedv2: rethinking overcooked for zero-shot coordination. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Gittins, J., Glazebrook, K., Weber, R.: Multi-Armed Bandit Allocation Indices. Wiley (2011)","DOI":"10.1002\/9780470980033"},{"issue":"2","key":"3_CR16","doi-asserted-by":"publisher","first-page":"627","DOI":"10.5465\/annals.2018.0057","volume":"14","author":"E Glikson","year":"2020","unstructured":"Glikson, E., Woolley, A.W.: Human trust in artificial intelligence: review of empirical research. Acad. Manag. Ann. 14(2), 627\u2013660 (2020)","journal-title":"Acad. Manag. Ann."},{"key":"3_CR17","unstructured":"Gu, S., et al.: A review of safe reinforcement learning: methods, theory and applications. arXiv preprint arXiv:2205.10330 (2022)"},{"key":"3_CR18","unstructured":"Hu, H., Lerer, A., Cui, B., Pineda, L., Brown, N., Foerster, J.: Off-belief learning. In: International Conference on Machine Learning, pp. 4369\u20134379. PMLR (2021)"},{"key":"3_CR19","unstructured":"Hu, H., Lerer, A., Peysakhovich, A., Foerster, J.: \u201cOther-play\u201d for zero-shot coordination. In: International Conference on Machine Learning, pp. 4399\u20134410. PMLR (2020)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1613\/jair.1.14174","volume":"76","author":"R Kirk","year":"2023","unstructured":"Kirk, R., Zhang, A., Grefenstette, E., Rockt\u00e4schel, T.: A survey of zero-shot generalisation in deep reinforcement learning. J. Artif. Intell. Res. 76, 201\u2013264 (2023)","journal-title":"J. Artif. Intell. Res."},{"key":"3_CR21","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.689550","volume":"8","author":"YL Kuo","year":"2021","unstructured":"Kuo, Y.L., Katz, B., Barbu, A.: Compositional RL agents that follow language commands in temporal logic. Front. Robot. AI 8, 689550 (2021)","journal-title":"Front. Robot. AI"},{"key":"3_CR22","unstructured":"Liu, B., Liu, Q., Stone, P., Garg, A., Zhu, Y., Anandkumar, A.: Coach-player multi-agent reinforcement learning for dynamic team composition. In: International Conference on Machine Learning, pp. 6860\u20136870. PMLR (2021)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: From motor control to team play in simulated humanoid football. Sci. Robot. 7(69), eabo0235 (2022)","DOI":"10.1126\/scirobotics.abo0235"},{"key":"3_CR24","unstructured":"MacGlashan, J., Littman, M., Loftin, R., Peng, B., Roberts, D., Taylor, M.: Training an agent to ground commands with reward and punishment. In: Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Mirsky, R., et al.: A survey of ad hoc teamwork research. In: European Conference on Multi-Agent Systems, pp. 275\u2013293. Springer (2022)","DOI":"10.1007\/978-3-031-20614-6_16"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"3_CR27","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1613\/jair.1.12889","volume":"73","author":"S Nashed","year":"2022","unstructured":"Nashed, S., Zilberstein, S.: A survey of opponent modeling in adversarial domains. J. Artif. Intell. Res. 73, 277\u2013327 (2022)","journal-title":"J. Artif. Intell. Res."},{"key":"3_CR28","unstructured":"Ndousse, K.K., Eck, D., Levine, S., Jaques, N.: Emergent social learning via multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 7991\u20138004. PMLR (2021)"},{"key":"3_CR29","unstructured":"Nekoei, H., Zhao, X., Rajendran, J., Liu, M., Chandar, S.: Towards few-shot coordination: revisiting ad-hoc teamplay challenge in the game of hanabi. In: Conference on Lifelong Learning Agents, pp. 861\u2013877. PMLR (2023)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Robbins, H.: Some aspects of the sequential design of experiments. American Mathematical Society (1952)","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Samuelson, L.: Evolutionary games and equilibrium selection, vol.\u00a01. MIT Press (1997)","DOI":"10.1109\/TEVC.1997.661553"},{"key":"3_CR32","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"3_CR33","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"2","key":"3_CR34","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1177\/0963721420984425","volume":"30","author":"N Sebanz","year":"2021","unstructured":"Sebanz, N., Knoblich, G.: Progress in joint-action research. Curr. Dir. Psychol. Sci. 30(2), 138\u2013143 (2021)","journal-title":"Curr. Dir. Psychol. Sci."},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Stone, P., Kaminka, G., Kraus, S., Rosenschein, J.: Ad hoc autonomous agent teams: collaboration without pre-coordination. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a024, pp. 1504\u20131509 (2010)","DOI":"10.1609\/aaai.v24i1.7529"},{"key":"3_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1613\/jair.1.13445","volume":"74","author":"SG Subramanian","year":"2022","unstructured":"Subramanian, S.G., Taylor, M.E., Larson, K., Crowley, M.: Multi-agent advisor Q-learning. J. Artif. Intell. Res. 74, 1\u201374 (2022)","journal-title":"J. Artif. Intell. Res."},{"key":"3_CR37","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"},{"issue":"3\u20134","key":"3_CR38","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/biomet\/25.3-4.285","volume":"25","author":"WR Thompson","year":"1933","unstructured":"Thompson, W.R.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25(3\u20134), 285\u2013294 (1933)","journal-title":"Biometrika"},{"key":"3_CR39","first-page":"4235","volume":"33","author":"N Vieillard","year":"2020","unstructured":"Vieillard, N., Pietquin, O., Geist, M.: Munchausen reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 4235\u20134246 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","DOI":"10.1038\/s41586-019-1724-z"},{"key":"3_CR41","unstructured":"Wang, C., Rahman, A., Durugkar, I., Liebman, E., Stone, P.: N-agent ad hoc teamwork. arXiv preprint arXiv:2404.10740 (2024)"},{"key":"3_CR42","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995\u20132003. PMLR (2016)"},{"key":"3_CR43","first-page":"7504","volume":"35","author":"S Xu","year":"2022","unstructured":"Xu, S., Wang, H., Wu, Y.: Grounded reinforcement learning: learning to win the game under human commands. Adv. Neural. Inf. Process. Syst. 35, 7504\u20137519 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR44","unstructured":"Xue, K., et al.: Heterogeneous multi-agent zero-shot coordination by coevolution. IEEE Trans. Evol. Comput. (2024)"},{"key":"3_CR45","unstructured":"Yan, X., Guo, J., Lou, X., Wang, J., Zhang, H., Du, Y.: An efficient end-to-end training approach for zero-shot human-ai coordination. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Yu, P., Mishra, M., Zaidi, S., Tokekar, P.: Tactic: task-agnostic contrastive pre-training for inter-agent communication. arXiv preprint arXiv:2501.02174 (2025)","DOI":"10.65109\/ZYQM8589"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Zhao, R., et al.: Maximum entropy population-based training for zero-shot human-ai coordination. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 6145\u20136153 (2023)","DOI":"10.1609\/aaai.v37i5.25758"},{"key":"3_CR48","unstructured":"Zhu, C., Dastani, M., Wang, S.: A survey of multi-agent reinforcement learning with communication. arXiv preprint arXiv:2203.08975 (2022)"}],"container-title":["Lecture Notes in Computer Science","Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XVIII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-17542-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T11:21:53Z","timestamp":1771068113000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-17542-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032175410","9783032175427"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-17542-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COINE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Detroit","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"coin2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/coin-workshop.github.io\/coine-2025-detroit\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}