{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:25:33Z","timestamp":1760171133176,"version":"3.37.3"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s10458-019-09404-2","type":"journal-article","created":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T03:00:47Z","timestamp":1551841247000},"page":"216-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A probabilistic argumentation framework for reinforcement learning agents"],"prefix":"10.1007","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4736-9214","authenticated-orcid":false,"given":"R\u00e9gis","family":"Riveret","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guido","family":"Governatori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonino","family":"Rotolo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeremy","family":"Pitt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Sartor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,3,6]]},"reference":[{"key":"9404_CR1","volume-title":"A theory of legal argumentation: The theory of rational discourse as theory of legal justification","author":"R Alexy","year":"1989","unstructured":"Alexy, R. (1989). A theory of legal argumentation: The theory of rational discourse as theory of legal justification. Oxford: Clarendon."},{"key":"9404_CR2","doi-asserted-by":"crossref","unstructured":"Amgoud, L. (2009). Argumentation for decision making. In Argumentation in artificial intelligence (pp. 301\u2013320). Springer.","DOI":"10.1007\/978-0-387-98197-0_15"},{"issue":"1","key":"9404_CR3","doi-asserted-by":"publisher","first-page":"1:1","DOI":"10.1145\/1459010.1459011","volume":"10","author":"A Artikis","year":"2009","unstructured":"Artikis, A., Sergot, M., & Pitt, J. (2009). Specifying norm-governed computational societies. ACM Transactions on Computational Logic, 10(1), 1:1\u20131:42.","journal-title":"ACM Transactions on Computational Logic"},{"key":"9404_CR4","doi-asserted-by":"crossref","unstructured":"Artikis, A., Sergot, M., Pitt, J., Busquets, D., & Riveret, R. (2016). Specifying and executing open multi-agent systems. In Social coordination frameworks for social technical systems (pp. 197\u2013212). Springer.","DOI":"10.1007\/978-3-319-33570-4_10"},{"issue":"3","key":"9404_CR5","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1609\/aimag.v38i3.2704","volume":"38","author":"K Atkinson","year":"2017","unstructured":"Atkinson, K., Baroni, P., Giacomin, M., Hunter, A., Prakken, H., Reed, C., et al. (2017). Towards artificial argumentation. AI Magazine, 38(3), 25\u201336.","journal-title":"AI Magazine"},{"issue":"10\u201315","key":"9404_CR6","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1016\/j.artint.2007.04.009","volume":"171","author":"K Atkinson","year":"2007","unstructured":"Atkinson, K., & Bench-Capon, T. J. M. (2007). Practical reasoning as presumptive argumentation using action based alternating transition systems. Artificial Intellignence, 171(10\u201315), 855\u2013874.","journal-title":"Artificial Intellignence"},{"issue":"4","key":"9404_CR7","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1017\/S0269888911000166","volume":"26","author":"P Baroni","year":"2011","unstructured":"Baroni, P., Caminada, M., & Giacomin, M. (2011). An introduction to argumentation semantics. The Knowledge Engineering Review, 26(4), 365\u2013410.","journal-title":"The Knowledge Engineering Review"},{"key":"9404_CR8","unstructured":"Baroni, P., Governatori, G., & Riveret, R. (2016). On labelling statements in multi-labelling argumentation. In Proceedings of the 22nd European conference on artificial intelligence (Vol. 285, pp. 489\u2013497). IOS Press."},{"issue":"10","key":"9404_CR9","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1073\/pnas.42.10.767","volume":"42","author":"R Bellman","year":"1956","unstructured":"Bellman, R. (1956). Dynamic programming and Lagrange multipliers. Proceedings of the National Academy of Sciences of the United States of America, 42(10), 767.","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"9404_CR10","doi-asserted-by":"crossref","unstructured":"Bench-Capon, T. J. M., & Atkinson, K. (2009). Abstract argumentation and values. In L.\u00a0Rahwan & G.\u00a0Simari (eds.) Argumentation in artificial intelligence. Springer.","DOI":"10.1007\/978-0-387-98197-0_3"},{"key":"9404_CR11","volume-title":"Dynamic programming and optimal control","author":"DP Bertsekas","year":"1995","unstructured":"Bertsekas, D. P. (1995). Dynamic programming and optimal control (Vol. 1). Belmont, MA: Athena Scientific."},{"issue":"1","key":"9404_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/19462166.2013.869764","volume":"5","author":"P Besnard","year":"2014","unstructured":"Besnard, P., Garc\u00eda, A. J., Hunter, A., Modgil, S., Prakken, H., Simari, G. R., et al. (2014). Introduction to structured argumentation. Argument & Computation, 5(1), 1\u20134.","journal-title":"Argument & Computation"},{"issue":"3\u20134","key":"9404_CR13","first-page":"428","volume":"2","author":"J Broersen","year":"2002","unstructured":"Broersen, J., Dastani, M., Hulstijn, J., & van der Torre, L. (2002). Goal generation in the BOID architecture. Cognitive Science Quarterly, 2(3\u20134), 428\u2013447.","journal-title":"Cognitive Science Quarterly"},{"key":"9404_CR14","unstructured":"Chen, S. H., & Huang, Y. C. (2005). Risk preference and survival dynamics. In: Agent-based simulation: From modeling methodologies to real-world applications, Agent-based social systems (Vol.\u00a01, pp. 135\u2013143). Tokyo: Springer."},{"key":"9404_CR15","volume-title":"Cognitive and social action","author":"R Conte","year":"1995","unstructured":"Conte, R., & Castelfranchi, C. (1995). Cognitive and social action. London: University College of London Press."},{"key":"9404_CR16","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1111\/j.1467-9337.2006.00342.x","volume":"19","author":"R Conte","year":"2006","unstructured":"Conte, R., & Castelfranchi, C. (2006). The mental path of norms. Ratio Juris, 19, 501\u2013517.","journal-title":"Ratio Juris"},{"issue":"1","key":"9404_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1023\/A:1008397328506","volume":"7","author":"R Conte","year":"1999","unstructured":"Conte, R., Falcone, R., & Sartor, G. (1999). Introduction: Agents and norms: How to fill the gap? Artificial Intelligence and Law, 7(1), 1\u201315.","journal-title":"Artificial Intelligence and Law"},{"key":"9404_CR18","volume-title":"Introduction to algorithms","author":"TH Cormen","year":"2001","unstructured":"Cormen, T. H., Leiserson, C. E., Rivest, R. L., Stein, C., et al. (2001). Introduction to algorithms (Vol. 2). Cambridge: MIT press."},{"issue":"2","key":"9404_CR19","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/0004-3702(94)00041-X","volume":"77","author":"PM Dung","year":"1995","unstructured":"Dung, P. M. (1995). On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artificial Intelligence, 77(2), 321\u2013358.","journal-title":"Artificial Intelligence"},{"key":"9404_CR20","doi-asserted-by":"crossref","unstructured":"Edmonds, B. (2004). How formal logic can fail to be useful for modelling or designing mas. In Regulated agent-based social systems, Lecture Notes in Computer Science (Vol. 2934, pp. 1\u201315). Springer.","DOI":"10.1007\/978-3-540-25867-4_1"},{"issue":"4","key":"9404_CR21","first-page":"1","volume":"7","author":"M Fasli","year":"2004","unstructured":"Fasli, M. (2004). Formal systems and agent-based social simulation equals null? Journal of Artificial Societies and Social Simulation, 7(4), 1\u20137.","journal-title":"Journal of Artificial Societies and Social Simulation"},{"key":"9404_CR22","doi-asserted-by":"crossref","unstructured":"Fornara, N., & Colombetti, M. (2009). Specifying and enforcing norms in artificial institutions. In Declarative agent languages and technologies VI, Lecture Notes in Computer Science (Vol. 5397, pp. 1\u201317). Springer.","DOI":"10.1007\/978-3-540-93920-7_1"},{"key":"9404_CR23","unstructured":"Fox, J., & Parsons, S. (1997). On using arguments for reasoning about actions and values. In Proceedings of the AAAI spring symposium on qualitative preferences in deliberation and practical reasoning."},{"key":"9404_CR24","unstructured":"Gao, Y., & Toni, F. (2014). Argumentation accelerated reinforcement learning for cooperativeulti-agent systems. In Proceedings of 21st European conference on artificial intelligence (pp. 333\u2013338). IOS Press."},{"key":"9404_CR25","unstructured":"Gao, Y., Toni, F., & Craven, R. (2012). Argumentation-based reinforcement learning for robocup soccer keepaway. In Proceedings of 20th European conference on artificial intelligence (pp. 342\u2013347). IOS Press."},{"key":"9404_CR26","unstructured":"Gaudou, B., Lorini, E., & Mayor, E. (2013). Moral guilt: An agent-based model analysis. In Advances in social simulation\u2014Proceedings of the 9th conference of the european social simulation association (pp. 95\u2013106)."},{"issue":"1","key":"9404_CR27","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/s10458-008-9030-4","volume":"17","author":"G Governatori","year":"2008","unstructured":"Governatori, G., & Rotolo, A. (2008). BIO logical agents: Norms, beliefs, intentions in defeasible logic. Autonomous Agents and Multi-Agent Systems, 17(1), 36\u201369.","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9404_CR28","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1613\/jair.5393","volume":"59","author":"A Hunter","year":"2017","unstructured":"Hunter, A., & Thimm, M. (2017). Probabilistic reasoning with abstract argumentation frameworks. Journal of Artificial Intelligence Research, 59, 565\u2013611.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9404_CR29","volume-title":"Probabilistic graphical models: Principles and techniques\u2014Adaptive computation and machine learning","author":"D Koller","year":"2009","unstructured":"Koller, D., & Friedman, N. (2009). Probabilistic graphical models: Principles and techniques\u2014Adaptive computation and machine learning. Cambridge: The MIT Press."},{"key":"9404_CR30","volume-title":"Linear algebra and geometry","author":"AI Kostrikin","year":"1997","unstructured":"Kostrikin, A. I., Manin, Y. I., & Alferieff, M. E. (1997). Linear algebra and geometry. Washington, DC: Gordon and Breach Science Publishers."},{"key":"9404_CR31","doi-asserted-by":"crossref","unstructured":"Modgil, S., & Caminada, M. (2009). Proof theories and algorithms for abstract argumentation frameworks. In Argumentation in artificial intelligence (pp. 105\u2013129). Springer.","DOI":"10.1007\/978-0-387-98197-0_6"},{"key":"9404_CR32","doi-asserted-by":"crossref","unstructured":"Muller, J., & Hunter, A. (2012). An argumentation-based approach for decision making. In 24th international conference on tools with artificial intelligence (Vol.\u00a01, pp. 564\u2013571). IEEE.","DOI":"10.1109\/ICTAI.2012.82"},{"key":"9404_CR33","unstructured":"Ng, A., Harada, D., & Russell, S. (1999). Policy invariance under reward transformations: theory and application to reward shaping. In Proceedings of 16th international conference on machine learning (pp. 278\u2013287)."},{"key":"9404_CR34","doi-asserted-by":"crossref","unstructured":"Ng, A. Y., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B., Berger, E., & Liang, E. (2006). Autonomous inverted helicopter flight via reinforcement learning. In Experimental robotics IX (pp. 363\u2013372). Springer.","DOI":"10.1007\/11552246_35"},{"key":"9404_CR35","first-page":"63","volume-title":"Argument schemes for normative practical reasoning","author":"N Oren","year":"2014","unstructured":"Oren, N. (2014). Argument schemes for normative practical reasoning (pp. 63\u201378). Berlin: Springer."},{"key":"9404_CR36","doi-asserted-by":"crossref","unstructured":"Parsons, S., & Fox, J. (1996). Argumentation and decision making: A position paper. In Practical reasoning (pp. 705\u2013709). Springer.","DOI":"10.1007\/3-540-61313-7_113"},{"key":"9404_CR37","volume-title":"Treatise of legal philosophy and general jurisprudence","author":"E Pattaro","year":"2005","unstructured":"Pattaro, E. (2005). The law and the right. In E. Pattaro (Ed.), Treatise of legal philosophy and general jurisprudence (Vol. 1). Berlin: Springer."},{"key":"9404_CR38","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1887.001.0001","volume-title":"Cognitive carpentry: A blueprint for how to build a person","author":"JL Pollock","year":"1995","unstructured":"Pollock, J. L. (1995). Cognitive carpentry: A blueprint for how to build a person. Cambridge, MA: MIT Press."},{"key":"9404_CR39","unstructured":"Prakken, H. (2006). Combining sceptical epistemic reasoning with credulous practical reasoning. In Proceedings of the 1st conference on computational models of argument (pp. 311\u2013322). IOS Press."},{"issue":"2","key":"9404_CR40","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1080\/19462160903564592","volume":"1","author":"H Prakken","year":"2011","unstructured":"Prakken, H. (2011). An abstract framework for argumentation with structured arguments. Argument and Computation, 1(2), 93\u2013124.","journal-title":"Argument and Computation"},{"issue":"1\u20132","key":"9404_CR41","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1080\/11663081.1997.10510900","volume":"7","author":"H Prakken","year":"1997","unstructured":"Prakken, H., & Sartor, G. (1997). Argument-based extended logic programming with defeasible priorities. Journal of Applied Non-Classical Logics, 7(1\u20132), 25\u201375.","journal-title":"Journal of Applied Non-Classical Logics"},{"key":"9404_CR42","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.artint.2015.06.005","volume":"227","author":"H Prakken","year":"2015","unstructured":"Prakken, H., & Sartor, G. (2015). Law and logic: A review from an argumentation perspective. Artificial Intelligence, 227, 214\u2013245.","journal-title":"Artificial Intelligence"},{"volume-title":"Argumentation in artificial Intelligence","year":"2009","key":"9404_CR43","unstructured":"Rahwan, I., & Simari, G. R. (Eds.). (2009). Argumentation in artificial Intelligence. Berlin: Springer."},{"issue":"1","key":"9404_CR44","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10472-018-9574-1","volume":"83","author":"R Riveret","year":"2018","unstructured":"Riveret, R., Baroni, P., Gao, Y., Governatori, G., Rotolo, A., & Sartor, G. (2018). A labelling framework for probabilistic argumentation. Annals of Mathamatics and Artificial Intelligence, 83(1), 21\u201371.","journal-title":"Annals of Mathamatics and Artificial Intelligence"},{"issue":"2","key":"9404_CR45","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1080\/19462166.2015.1107134","volume":"6","author":"R Riveret","year":"2015","unstructured":"Riveret, R., Korkinof, D., Draief, M., & Pitt, J. V. (2015). Probabilistic abstract argumentation: An investigation with boltzmann machines. Argumentation & Computation, 6(2), 178\u2013218.","journal-title":"Argumentation & Computation"},{"key":"9404_CR46","unstructured":"Riveret, R., Pitt, J. V., Korkinof, D., & Draief, M. (2015). Neuro-symbolic agents: Boltzmann machines and probabilistic abstract argumentation with sub-arguments. In Proceedings of the 14th international conference on autonomous agents and multiagent systems (pp. 1481\u20131489). ACM."},{"issue":"4","key":"9404_CR47","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s10506-012-9134-7","volume":"20","author":"R Riveret","year":"2012","unstructured":"Riveret, R., Rotolo, A., & Sartor, G. (2012). Probabilistic rule-based argumentation for norm-governed learning agents. Artificial Intelligence and Law, 20(4), 383\u2013420.","journal-title":"Artificial Intelligence and Law"},{"key":"9404_CR48","volume-title":"On law and justice","author":"A Ross","year":"1958","unstructured":"Ross, A. (1958). On law and justice. London: Stevens."},{"key":"9404_CR49","unstructured":"Rummery, G. A., & Niranjan, M. (1994). On-line Q-learning using connectionist systems. Technical report. University of Cambridge."},{"key":"9404_CR50","volume-title":"Legal reasoning: A cognitive approach to the law","author":"G Sartor","year":"2005","unstructured":"Sartor, G. (2005). Legal reasoning: A cognitive approach to the law. Berlin: Springer."},{"key":"9404_CR51","doi-asserted-by":"crossref","unstructured":"Shams, Z., Vos, M. D., Oren, N., Padget, J., & Satoh, K. (2015). Argumentation-based normative practical reasoning. In Proceedings of the 3rd international workshop on theory and applications of formal argumentation, revised selected papers (pp. 226\u2013242). Springer.","DOI":"10.1007\/978-3-319-28460-6_14"},{"issue":"3","key":"9404_CR52","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10472-015-9476-4","volume":"76","author":"GI Simari","year":"2016","unstructured":"Simari, G. I., Shakarian, P., & Falappa, M. A. (2016). A quantitative approach to belief revision in structured probabilistic argumentation. Annals of Mathematics and Artificial Intelligence, 76(3), 375\u2013408.","journal-title":"Annals of Mathematics and Artificial Intelligence"},{"key":"9404_CR53","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1177\/105971230501300301","volume":"13","author":"P Stone","year":"2005","unstructured":"Stone, P., Sutton, R. S., & Kuhlmann, G. (2005). Reinforcement learning for robocup soccer keepaway. Adaptive Behavior, 13, 165\u2013188.","journal-title":"Adaptive Behavior"},{"key":"9404_CR54","volume-title":"Reinforcement learning: An introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R. S., & Barto, A. (1998). Reinforcement learning: An introduction. Cambridge: MIT Press."},{"key":"9404_CR55","unstructured":"Tadepalli, P., Givan, R., & Driessens, K. (2004). Relational reinforcement learning: An overview. In Proceedings of the ICML04 workshop on relational reinforcement learning."},{"issue":"1","key":"9404_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11229-006-9072-6","volume":"156","author":"W Hoek van der","year":"2007","unstructured":"van der Hoek, W., Roberts, M., & Wooldridge, M. (2007). Social laws in alternating time: Effectiveness, feasibility, and synthesis. Synthese, 156(1), 1\u201319.","journal-title":"Synthese"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-019-09404-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-019-09404-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-019-09404-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,5]],"date-time":"2020-03-05T00:14:35Z","timestamp":1583367275000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-019-09404-2"}},"subtitle":["Towards a mentalistic approach to agent profiles"],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":56,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["9404"],"URL":"https:\/\/doi.org\/10.1007\/s10458-019-09404-2","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"type":"print","value":"1387-2532"},{"type":"electronic","value":"1573-7454"}],"subject":[],"published":{"date-parts":[[2019,3]]},"assertion":[{"value":"6 March 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}