{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T08:17:44Z","timestamp":1767860264484,"version":"3.49.0"},"reference-count":33,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T00:00:00Z","timestamp":1687737600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Theory and Practice of Logic Programming"],"published-print":{"date-parts":[[2023,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Ad hoc teamwork (AHT) refers to the problem of enabling an agent to collaborate with teammates without prior coordination. State of the art methods in AHT are <jats:italic>data-driven<\/jats:italic>, using a large labeled dataset of prior observations to model the behavior of other agent <jats:italic>types<\/jats:italic> and to determine the ad hoc agent\u2019s behavior. These methods are computationally expensive, lack transparency, and make it difficult to adapt to previously unseen changes. Our recent work introduced an architecture that determined an ad hoc agent\u2019s behavior based on non-monotonic logical reasoning with prior commonsense domain knowledge and models learned from limited examples to predict the behavior of other agents. This paper describes KAT, a knowledge-driven architecture for AHT that substantially expands our prior architecture\u2019s capabilities to support: (a) online selection, adaptation, and learning of the behavior prediction models; and (b) collaboration with teammates in the presence of partial observability and limited communication. We illustrate and experimentally evaluate KAT\u2019s capabilities in two simulated benchmark domains for multiagent collaboration: Fort Attack and Half Field Offense. We show that KAT\u2019s performance is better than a purely knowledge-driven baseline, and comparable with or better than a state of the art data-driven baseline, particularly in the presence of limited training data, partial observability, and changes in team composition.<\/jats:p>","DOI":"10.1017\/s1471068423000091","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T05:16:33Z","timestamp":1687756593000},"page":"696-714","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":6,"title":["Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork"],"prefix":"10.1017","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2302-1501","authenticated-orcid":false,"given":"HASRA","family":"DODAMPEGAMA","sequence":"first","affiliation":[]},{"given":"MOHAN","family":"SRIDHARAN","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2023,6,26]]},"reference":[{"key":"S1471068423000091_ref15","doi-asserted-by":"publisher","DOI":"10.4324\/9781315658353-2"},{"key":"S1471068423000091_ref14","first-page":"34","article-title":"Towards a Rational Theory of Heuristics","author":"Gigerenzer","year":"2016","journal-title":"Palgrave Macmillan UK"},{"key":"S1471068423000091_ref19","doi-asserted-by":"crossref","unstructured":"Macke, W. , Mirsky, R. and Stone, P. 2021. Expected value of communication for planning in ad hoc teamwork. In AAAI Conference on Artificial Intelligence, 11290\u201311298.","DOI":"10.1609\/aaai.v35i13.17346"},{"key":"S1471068423000091_ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-018-0546-8"},{"key":"S1471068423000091_ref11","doi-asserted-by":"crossref","unstructured":"Dodampegama, H. and Sridharan, M. 2023a. Back to the future: Toward a hybrid architecture for ad hoc teamwork. In AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v37i1.25070"},{"key":"S1471068423000091_ref4","unstructured":"Baral, C. , Gelfond, G. , Son, T. C. and Pontelli, E. 2010. Using answer set programming to model multi-agent scenarios involving agents\u2019 knowledge about other\u2019s knowledge. In Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, Vol. 1. 259\u2013266."},{"key":"S1471068423000091_ref22","unstructured":"Rahman, M. A. , Hopner, N. , Christianos, F. and Albrecht, S. V. 2021. Towards open ad hoc teamwork using graph-based policy learning. In International Conference on Machine Learning, 8776\u20138786."},{"key":"S1471068423000091_ref30","doi-asserted-by":"crossref","unstructured":"Stone, P. , Kaminka, G. , Kraus, S. and Rosenschein, J. 2010. Ad Hoc Autonomous Agent Teams: Collaboration without Pre-Coordination. In AAAI Conference on Artificial Intelligence, 1504\u20131509.","DOI":"10.1609\/aaai.v24i1.7529"},{"key":"S1471068423000091_ref25","first-page":"1","volume-title":"Computational Logic in Multi-Agent Systems","author":"Son","year":"2010"},{"key":"S1471068423000091_ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16867-3_3"},{"key":"S1471068423000091_ref13","first-page":"105","article-title":"Some properties of system descriptions of","volume":"1\u20132","author":"Gelfond","year":"2013","journal-title":"Applied Non-Classical Logics, Special Issue on Equilibrium Logic and ASP 23"},{"key":"S1471068423000091_ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-120709-145346"},{"key":"S1471068423000091_ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20614-6_16"},{"key":"S1471068423000091_ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09584-4"},{"key":"S1471068423000091_ref23","doi-asserted-by":"crossref","unstructured":"Santos, P. M. , Ribeiro, J. G. , Sardinha, A. and Melo, F. S. 2021. Ad hoc teamwork in the presence of non-stationary teammates. In Progress in Artificial Intelligence, Marreiros, G. , Melo, F. S. , Lau, N. , Lopes Cardoso, H. , and Reis, L. P. , Eds. Springer International, 648\u2013660.","DOI":"10.1007\/978-3-030-86230-5_51"},{"key":"S1471068423000091_ref2","unstructured":"Balduccini, M. and Gelfond, M. 2003. Logic programs with consistency-restoring rules. In AAAI Spring Symposium on Logical Formalization of Commonsense Reasoning."},{"key":"S1471068423000091_ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11355-0_13"},{"key":"S1471068423000091_ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78743-1_2"},{"key":"S1471068423000091_ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.10.005"},{"key":"S1471068423000091_ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103601"},{"key":"S1471068423000091_ref9","doi-asserted-by":"crossref","unstructured":"Chen, S. , Andrejczuk, E. , Cao, Z. and Zhang, J. 2020. AATEAM: Achieving the ad hoc teamwork by employing the attention mechanism. In AAAI Conference on Artificial Intelligence, 7095\u20137102.","DOI":"10.1609\/aaai.v34i05.6196"},{"key":"S1471068423000091_ref32","unstructured":"Zand, J. , Parker-Holder, J. and Roberts, S. J. 2022. On-the-fly strategy adaptation for ad-hoc agent coordination. In International Conference on Autonomous Agents and Multiagent Systems, 1771\u20131773."},{"key":"S1471068423000091_ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11524"},{"key":"S1471068423000091_ref18","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/11790.001.0001"},{"key":"S1471068423000091_ref31","unstructured":"Wu, F. , Zilberstein, S. and Chen, X. 2011. Online planning for ad hoc autonomous agent teams. In International Joint Conference on Artificial Intelligence, 439\u2013445."},{"key":"S1471068423000091_ref33","unstructured":"Zintgraf, L. , Devlin, S. , Ciosek, K. , Whiteson, S. and Hofmann, K. 2021. Deep interactive Bayesian reinforcement learning via meta-learning. In International Conference on Autonomous Agents and Multiagent Systems."},{"key":"S1471068423000091_ref28","first-page":"77","article-title":"Knowledge representation and interactive learning of domain knowledge for human-robot collaboration","volume":"7","author":"Sridharan","year":"2018","journal-title":"Advances in Cognitive Systems"},{"key":"S1471068423000091_ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40564-8_14"},{"key":"S1471068423000091_ref8","unstructured":"Bowling, M. and McCracken, P. 2005. Coordination and adaptation in impromptu teams. In National Conference on Artificial Intelligence, 53\u201358."},{"key":"S1471068423000091_ref12","unstructured":"Dodampegama, H. and Sridharan, M. 2023b. Code. https:\/\/github.com\/hharithaki\/KAT."},{"key":"S1471068423000091_ref7","doi-asserted-by":"crossref","unstructured":"Barrett, S. , Stone, P. , Kraus, S. and Rosenfeld, A. 2013. Teamwork with limited knowledge of teammates. In AAAI Conference on Artificial Intelligence, Vol. 27, 102\u2013108.","DOI":"10.1609\/aaai.v27i1.8659"},{"key":"S1471068423000091_ref17","unstructured":"Hausknecht, M. , Mupparaju, P. , Subramanian, S. , Kalyanakrishnan, S. and Stone, P. 2016. Half field offense: An environment for multiagent learning and ad hoc teamwork. In AAMAS Adaptive Learning Agents Workshop."},{"key":"S1471068423000091_ref21","first-page":"242","article-title":"Integrated commonsense reasoning and deep learning for transparent decision making in robotics","volume":"2","author":"Mota","year":"2021","journal-title":"Springer Nature CS"}],"container-title":["Theory and Practice of Logic Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1471068423000091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T09:38:28Z","timestamp":1709026708000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1471068423000091\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,26]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["S1471068423000091"],"URL":"https:\/\/doi.org\/10.1017\/s1471068423000091","relation":{},"ISSN":["1471-0684","1475-3081"],"issn-type":[{"value":"1471-0684","type":"print"},{"value":"1475-3081","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,26]]},"assertion":[{"value":"\u00a9 The Author(s), 2023. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http:\/\/creativecommons.org\/licenses\/by\/4.0\/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}