{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:18:42Z","timestamp":1780503522864,"version":"3.54.1"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031206139","type":"print"},{"value":"9783031206146","type":"electronic"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20614-6_16","type":"book-chapter","created":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T16:02:37Z","timestamp":1670688157000},"page":"275-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["A Survey of\u00a0Ad Hoc Teamwork Research"],"prefix":"10.1007","author":[{"given":"Reuth","family":"Mirsky","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ignacio","family":"Carlucho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arrasy","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elliot","family":"Fosong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Macke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohan","family":"Sridharan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano V.","family":"Albrecht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,11]]},"reference":[{"key":"16_CR1","unstructured":"Agmon, N., Barrett, S., Stone, P.: Modeling uncertainty in leading ad hoc teams. In: The International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2014, pp. 397\u2013404 (2014)"},{"key":"16_CR2","unstructured":"Albrecht, S.V., Ramamoorthy, S.: Comparative evaluation of MAL algorithms in a diverse set of ad hoc team problems. In: The International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2012 (2012)"},{"key":"16_CR3","unstructured":"Albrecht, S.V., Ramamoorthy, S.: A game-theoretic model and best-response learning method for ad hoc coordination in multiagent systems. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2013, pp. 1155\u20131156, Richland, SC, 2013. International Foundation for Autonomous Agents and Multiagent Systems (2013). ISBN 9781450319935"},{"key":"16_CR4","unstructured":"Albrecht, S.V., Stone, P.: Reasoning about hypothetical agent behaviours and their parameters. In: The International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2017, pp. 547\u2013555 (2017)"},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","volume":"258","author":"SV Albrecht","year":"2018","unstructured":"Albrecht, S.V., Stone, P.: Autonomous agents modelling other agents: a comprehensive survey and open problems. Artif. Intell. 258, 66\u201395 (2018)","journal-title":"Artif. Intell."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Albrecht, S.V., Crandall, J.W., Ramamoorthy, S.: An empirical study on the practical impact of prior beliefs over policy types. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence, pp. 1988\u20131994 (2015a)","DOI":"10.1609\/aaai.v29i1.9426"},{"key":"16_CR7","unstructured":"Albrecht, S.V., Crandall, J.W., Ramamoorthy, S.: E-HBA: using action policies for expert advice and agent typification. In: AAAI Workshop on Multiagent Interaction without Prior Coordination, p. 7 (2015b)"},{"key":"16_CR8","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.artint.2016.02.004","volume":"235","author":"SV Albrecht","year":"2016","unstructured":"Albrecht, S.V., Crandall, J.W., Ramamoorthy, S.: Belief and truth in hypothesised behaviours. Artif. Intell. 235, 63\u201394 (2016)","journal-title":"Artif. Intell."},{"issue":"4","key":"16_CR9","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s10458-016-9358-0","volume":"31","author":"SV Albrecht","year":"2017","unstructured":"Albrecht, S.V., Liemhetcharat, S., Stone, P.: Special issue on multiagent interaction without prior coordination: guest editorial. Autonom. Agents Multi-Agent Syst. 31(4), 765\u2013766 (2017). https:\/\/doi.org\/10.1007\/s10458-016-9358-0","journal-title":"Autonom. Agents Multi-Agent Syst."},{"key":"16_CR10","unstructured":"Alford, R., Borck, H., Karneeb, J.: Active behavior recognition in beyond visual range air combat. In: Proceedings of the 3rd Annual Conference on Advances in Cognitive Systems. Cognitive Systems Foundation (2015)"},{"key":"16_CR11","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."},{"key":"16_CR12","unstructured":"Barrett, S., Stone, P.: Cooperating with unknown teammates in robot soccer. In: AAAI Workshop on Multiagent Interaction without Prior Coordination, p. 6 (2014)"},{"key":"16_CR13","unstructured":"Barrett, S., Stone, P., Kraus, S.: Empirical evaluation of ad hoc teamwork in the pursuit domain. In: The International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2011, vol. 2, pp. 567\u2013574 (2011)"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Barrett, S., Agmon, N., Hazon, N., Kraus, S., Stone, P.: Communicating with unknown teammates. In: The European Conference on Artificial Intelligence, ECAI 2014, volume 263 of Frontiers in Artificial Intelligence and Applications, pp. 45\u201350. IOS Press (2014). https:\/\/doi.org\/10.3233\/978-1-61499-419-0-45","DOI":"10.3233\/978-1-61499-419-0-45"},{"key":"16_CR15","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.artint.2016.10.005","volume":"242","author":"S Barrett","year":"2017","unstructured":"Barrett, S., Rosenfeld, A., Kraus, S., Stone, P.: Making friends on the fly: cooperating with new teammates. Artif. Intell. 242, 132\u2013171 (2017). https:\/\/doi.org\/10.1016\/j.artint.2016.10.005","journal-title":"Artif. Intell."},{"key":"16_CR16","unstructured":"Bowling, M., McCracken, P.: Coordination and adaptation in impromptu teams. In: National Conference on Artificial Intelligence, vol. 1 of AAAI 2005, pp. 53\u201358 (2005)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Breazeal, C., Kidd, C.D., Thomaz, A.L., Hoffman, G., Berlin, M.: Effects of nonverbal communication on efficiency and robustness in human-robot teamwork. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 708\u2013713. IEEE (2005)","DOI":"10.1109\/IROS.2005.1545011"},{"key":"16_CR18","unstructured":"Bullard, K., Meier, F., Kiela, D., Pineau, J., Foerster, J.: Exploring zero-shot emergent communication in embodied multi-agent populations. arXiv:2010.15896 (2020)"},{"key":"16_CR19","unstructured":"Bullard, K., Kiela, D., Meier, F., Pineau, J., Foerster, J.: Quasi-equivalence discovery for zero-shot emergent communication. arXiv:2103.08067 (2021)"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C (App. Rev.) 38(2), 156\u2013172 (2008). https:\/\/doi.org\/10.1109\/TSMCC.2007.913919","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Canaan, R., Gao, X., Togelius, J., Nealen, A., Menzel, S.: Generating and adapting to diverse ad-hoc cooperation agents in Hanabi. arXiv:2004.13710 (2020)","DOI":"10.1109\/CIG.2019.8847944"},{"key":"16_CR22","unstructured":"Chakraborty, D., Stone, P.: Cooperating with a Markovian Ad hoc teammate. In: Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems, vol. 1, AAMAS 2013, pp. 1085\u20131092. International Foundation for Autonomous Agents and Multiagent Systems (2013)"},{"key":"16_CR23","unstructured":"Chandrasekaran, M., Eck, A., Doshi, P., Soh, L.: Individual planning in open and typed agent systems. In: Thirty-Second Conference on Uncertainty in Artificial Intelligence, UAI 2016, pp. 82\u201391 (2016)"},{"key":"16_CR24","doi-asserted-by":"publisher","first-page":"7095","DOI":"10.1609\/aaai.v34i05.6196","volume":"34","author":"S Chen","year":"2020","unstructured":"Chen, S., Andrejczuk, E., Cao, Z., Zhang, J.: AATEAM: achieving the ad hoc teamwork by employing the attention mechanism. AAAI Conf. Artif. Intell. 34, 7095\u20137102 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i05.6196","journal-title":"AAAI Conf. Artif. Intell."},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Collins, J., Chand, S., Vanderkop, A., Howard, D.: A review of physics simulators for robotic applications. IEEE Access (2021)","DOI":"10.1109\/ACCESS.2021.3068769"},{"key":"16_CR26","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1017\/S0269888915000181","volume":"1","author":"S Devlin","year":"2016","unstructured":"Devlin, S., Kudenko, D.: Plan-based reward shaping for multi-agent reinforcement learning. Knowl. Eng. Revi. 1, 44\u201358 (2016)","journal-title":"Knowl. Eng. Revi."},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Dragan, A.D., Lee, K.C., Srinivasa, S.S.: Legibility and predictability of robot motion. In: ACM\/IEEE International Conference on Human-Robot Interaction, pp. 301\u2013308. IEEE (2013)","DOI":"10.1109\/HRI.2013.6483603"},{"key":"16_CR28","doi-asserted-by":"publisher","unstructured":"Eck, A., Shah, M., Doshi, P., Soh, L.-K.: Scalable decision-theoretic planning in open and typed multiagent systems. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 7127\u20137134. AAAI Press (2020). https:\/\/doi.org\/10.1609\/aaai.v34i05.6200","DOI":"10.1609\/aaai.v34i05.6200"},{"key":"16_CR29","doi-asserted-by":"publisher","unstructured":"Genter, K., Stone, P.: Influencing a Flock via Ad Hoc Teamwork. In: Swarm Intelligence, vol. 8667, pp. 110\u2013121. Springer International Publishing (2014). https:\/\/doi.org\/10.1007\/978-3-319-09952-1_10","DOI":"10.1007\/978-3-319-09952-1_10"},{"key":"16_CR30","unstructured":"Genter, K., Stone, P.: Adding influencing agents to a flock. In: The International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2017, pp. 615\u2013623 (2016)"},{"key":"16_CR31","unstructured":"Genter, K., Zhang, S., Stone, P.: Determining placements of influencing agents in a flock. In: Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems, pp. 247\u2013255. International Foundation for Autonomous Agents and Multiagent Systems (2015)"},{"issue":"4","key":"16_CR32","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1007\/s10458-016-9353-5","volume":"31","author":"K Genter","year":"2017","unstructured":"Genter, K., Laue, T., Stone, P.: Three years of the RoboCup standard platform league drop-in player competition: creating and maintaining a large scale ad hoc teamwork robotics competition. Autonom. Agents Multi-Agent Syst. 31(4), 790\u2013820 (2017). https:\/\/doi.org\/10.1007\/s10458-016-9353-5","journal-title":"Autonom. Agents Multi-Agent Syst."},{"key":"16_CR33","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1613\/jair.1579","volume":"24","author":"PJ Gmytrasiewicz","year":"2005","unstructured":"Gmytrasiewicz, P.J., Doshi, P.: A framework for sequential planning in multi-agent settings. J. Artif. Intell. Res. 24, 49\u201379 (2005). https:\/\/doi.org\/10.1613\/jair.1579","journal-title":"J. Artif. Intell. Res."},{"key":"16_CR34","doi-asserted-by":"publisher","unstructured":"Grosz, B.J., Kraus, S.: The evolution of Sharedplans. In: Foundations of Rational Agency, vol. 14, Applied Logic Series, pp. 227\u2013262. Springer, Netherlands (1999).https:\/\/doi.org\/10.1007\/978-94-015-9204-8_10","DOI":"10.1007\/978-94-015-9204-8_10"},{"key":"16_CR35","unstructured":"Hu, H., Lerer, A., Peysakhovich, A., Foerster, J.: \u201cOther-play\u201d for zero-shot coordination. Int. Conf. Mach. Learn. 119, 4399\u20134410 (2020)"},{"key":"16_CR36","first-page":"4369","volume":"139","author":"H Hu","year":"2021","unstructured":"Hu, H., Lerer, A., Cui, B., Pineda, L., Brown, N., Foerster, J.: Off-belief learning. Int. Conf. Mach. Learn. 139, 4369\u20134379 (2021)","journal-title":"Int. Conf. Mach. Learn."},{"key":"16_CR37","unstructured":"Khetarpal, K., Riemer, M., Rish, I., Precup, D.: Towards continual reinforcement learning: a review and perspectives. arXiv:2012.13490 (2020)"},{"key":"16_CR38","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29"},{"key":"16_CR39","unstructured":"Leibo, J.Z., et al.: Scalable evaluation of multi-agent reinforcement learning with Melting Pot. In: International Conference on Machine Learning, pp. 6187\u20136199 (2021)"},{"key":"16_CR40","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1109\/THMS.2021.3107675","volume":"51","author":"H Li","year":"2021","unstructured":"Li, H., et al.: Individualized mutual adaptation in human-agent teams. IEEE Trans. Human Mach. Syst. 51, 706\u2013714 (2021)","journal-title":"IEEE Trans. Human Mach. Syst."},{"issue":"4","key":"16_CR41","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1007\/s10458-016-9355-3","volume":"31","author":"S Liemhetcharat","year":"2017","unstructured":"Liemhetcharat, S., Veloso, M.: Allocating training instances to learning agents for team formation. Autonom. Agents Multi-Agent Syst. 31(4), 905\u2013940 (2017). https:\/\/doi.org\/10.1007\/s10458-016-9355-3","journal-title":"Autonom. Agents Multi-Agent Syst."},{"key":"16_CR42","unstructured":"Lupu, A., Cui, B., Hu, H., Foerster, J.: Trajectory diversity for zero-shot coordination. In: Proceedings of the 38th International Conference on Machine Learning, pp. 7204\u20137213 (2021)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Macke, W., Mirsky, R., Stone, P.: Expected value of communication for planning in ad hoc teamwork. In: The AAAI Conference on Artificial Intelligence, AAAI, vol. 35, pp. 10 (2021)","DOI":"10.1609\/aaai.v35i13.17346"},{"key":"16_CR44","unstructured":"Malik, D., Palaniappan, M., Fisac, J.F., Hadfield-Menell, D., Russell, S., Dragan, A.D.: An efficient, generalized Bellman update for cooperative inverse reinforcement learning. arXiv:1806.03820 (2018)"},{"key":"16_CR45","unstructured":"Mead, R., Weinberg, J.B.: Impromptu teams of heterogeneous mobile robots. In: The AAAI Conference on Artificial Intelligence, AAAI (2007)"},{"issue":"2","key":"16_CR46","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s10458-015-9280-x","volume":"30","author":"FS Melo","year":"2016","unstructured":"Melo, F.S., Sardinha, A.: Ad hoc teamwork by learning teammates\u2019 task. Autonom. Agents Multi-Agent Syst. 30(2), 175\u2013219 (2016). https:\/\/doi.org\/10.1007\/s10458-015-9280-x","journal-title":"Autonom. Agents Multi-Agent Syst."},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Mirsky, R., Macke, W., Wang, A., Yedidsion, H., Stone, P.: A penny for your thoughts: The value of communication in ad hoc teamwork. In: The International Joint Conference on Artificial Intelligence, IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/36"},{"key":"16_CR48","unstructured":"Mirsky, R., Xiao, X., Hart, J., Stone, P.: Prevention and resolution of conflicts in social navigation-a survey. arXiv preprint arXiv:2106.12113 (2021)"},{"key":"16_CR49","unstructured":"Open-Ended Learning Team, Stooke, A., et al.: Open-ended learning leads to generally capable agents. arXiv:2107.12808 (2021)"},{"key":"16_CR50","unstructured":"Papoudakis, G., Christianos, F., Rahman, A., Albrecht, S.V.: Dealing with non-stationarity in multi-agent deep reinforcement learning. arXiv:abs\/1906.04737 (2019)"},{"key":"16_CR51","unstructured":"Papoudakis, G., Christianos, F., Albrecht, S.V.: Local information agent modelling in partially-observable environments. arXiv:2006.09447 (2021)"},{"key":"16_CR52","unstructured":"Rabinowitz, N., Perbet, F., Song, F., Zhang, C., Eslami, S.M.A., Botvinick, M.: Machine theory of mind. In: International Conference on Machine Learning, pp. 4218\u20134227. PMLR (2018)"},{"key":"16_CR53","unstructured":"Rahman, A., H\u00f6pner, N., Christianos, F., Albrecht, S.V.: Towards open ad hoc teamwork using graph-based policy learning. In: International Conference on Machine Learning, vol. 139. PMLR (2021)"},{"key":"16_CR54","unstructured":"Rahman, A., Fosong, E., Carlucho, I., Albrecht, S.V.: Towards robust ad hoc teamwork agents by creating diverse training teammates. In: IJCAI Workshop on Ad Hoc Teamwork (2022)"},{"key":"16_CR55","doi-asserted-by":"publisher","unstructured":"Ravula, M., Alkoby, S., Stone, P.: Ad hoc teamwork with behavior switching agents. In: International Joint Conference on Artificial Intelligence, pp. 550\u2013556 (2019). https:\/\/doi.org\/10.24963\/ijcai.2019\/78","DOI":"10.24963\/ijcai.2019\/78"},{"key":"16_CR56","doi-asserted-by":"crossref","unstructured":"Ribeiro, J.G., Martinho, C., Sardinha, A., Melo, F.S.: Assisting Unknown Teammates in Unknown Tasks: Ad Hoc Teamwork under Partial Observability. arXiv:2201.03538 (2022)","DOI":"10.3233\/FAIA230486"},{"key":"16_CR57","unstructured":"Rovatsos, M., Wolf, M.: Towards social complexity reduction in multiagent learning: the ad hoc approach. Technical report SS-02-02, AAAI Press (2002)"},{"key":"16_CR58","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Series in Artificial Intelligence. Pearson, 4th edition edn. (2021)"},{"key":"16_CR59","doi-asserted-by":"crossref","unstructured":"Santos, P.M., Ribeiro, J.G., Sardinha, A., Melo, F.S.: Ad hoc teamwork in the presence of non-stationary teammates. In: Progress in Artificial Intelligence (2021)","DOI":"10.1007\/978-3-030-86230-5_51"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Sarratt, T.: Tuning belief revision for coordination with inconsistent teammates. In: AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, pp. 177\u2013183 (2015)","DOI":"10.1609\/aiide.v11i1.12797"},{"key":"16_CR61","unstructured":"Shu, T., Tian, Y.: M3rl: mind-aware multi-agent management reinforcement learning. In: International Conference on Learning Representations (2019)"},{"key":"16_CR62","doi-asserted-by":"crossref","unstructured":"Shvo, M., McIlraith, S.A.: Active goal recognition. n: The AAAI Conference on Artificial Intelligence, AAAI 34, pp. 9957\u20139966 (2020)","DOI":"10.1609\/aaai.v34i06.6551"},{"key":"16_CR63","doi-asserted-by":"publisher","unstructured":"Stone, P., Kaminka, G.A., Kraus, S., Rosenschein, J.S.: Ad hoc autonomous agent teams: collaboration without pre-coordination. In: AAAI Conference on Artificial Intelligence, pp. 1504\u20131509 (2010). https:\/\/doi.org\/10.5555\/2898607.2898847","DOI":"10.5555\/2898607.2898847"},{"key":"16_CR64","unstructured":"Suriadinata, J., Macke, W., Mirsky, R., Stone, P.: Reasoning about human behavior in ad hoc teamwork. In: Adaptive and learning Agents Workshop at AAMAS 2021, p. 6 (2021)"},{"issue":"1","key":"16_CR65","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"16_CR66","unstructured":"Vezhnevets, A., Wu, Y., Eckstein, M., Leblond, R., Leibo, J.Z.: OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 9733\u20139742 (2020)"},{"issue":"2","key":"16_CR67","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1111\/tops.12525","volume":"13","author":"RE Wang","year":"2021","unstructured":"Wang, R.E., Wu, S.A., Evans, J.A., Tenenbaum, J.B., Parkes, D.C., Kleiman-Weiner, M.: Too many cooks: Bayesian inference for coordinating multi-agent collaboration. Top. Cogn. Sci. 13(2), 414\u2013432 (2021). https:\/\/doi.org\/10.1111\/tops.12525","journal-title":"Top. Cogn. Sci."},{"key":"16_CR68","doi-asserted-by":"publisher","unstructured":"Wu, F., Zilberstein, S., Chen, X.: Online planning for ad hoc autonomous agent teams. In: International Joint Conference on Artificial Intelligence, pp. 439\u2013445 (2011). https:\/\/doi.org\/10.5591\/978-1-57735-516-8\/IJCAI11-081","DOI":"10.5591\/978-1-57735-516-8\/IJCAI11-081"},{"key":"16_CR69","unstructured":"Xie, A., Losey, D.P., Tolsma, R., Finn, C., Sadigh, D.: Learning latent representations to influence multi-agent interaction. In: Proceedings of the Conference on Robot Learning. PMLR (2020)"},{"key":"16_CR70","doi-asserted-by":"publisher","unstructured":"Yourdshahi, E.S., Pinder, T., Dhawan, G., Marcolino, L.S., Angelov, P.: Towards large scale ad-hoc teamwork. In: 2018 IEEE International Conference on Agents, pp. 44\u201349. IEEE (2018). https:\/\/doi.org\/10.1109\/AGENTS.2018.8460136","DOI":"10.1109\/AGENTS.2018.8460136"},{"key":"16_CR71","unstructured":"Zintgraf, L., Devlin, S., Ciosek, K., Whiteson, S., Hofmann, K.: Deep interactive Bayesian reinforcement learning via meta-learning. arXiv:2101.03864 (2021)"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20614-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T19:53:57Z","timestamp":1701546837000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20614-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031206139","9783031206146"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20614-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EUMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"D\u00fcsseldorf","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"14 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eumas2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ccc.cs.hhu.de\/eumas2022\/","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":"36","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":"23","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":"64% - 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)"}}]}}