{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:40:40Z","timestamp":1723016440492},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9]]},"abstract":"This paper presents ORLA (Online Reinforcement Learning Argumentation), a new approach for learning explainable symbolic argumentation models through direct exploration of the world. ORLA takes a set of expert arguments that promote some action in the world, and uses reinforcement learning to determine which of those arguments are the most effective for performing a task by maximizing a performance score. Thus, ORLA learns a preference ranking over the expert arguments such that the resulting value-based argumentation framework (VAF) can be used as a reasoning engine to select actions for performing the task. Although model-extraction methods exist that extract a VAF by mimicking the behavior of some non-symbolic model (e.g., a neural network), these extracted models are only approximations to their non-symbolic counterparts, which may result in both a performance loss and non-faithful explanations. Conversely, ORLA learns a VAF through direct interaction with the world (online learning), thus producing faithful explanations without sacrificing performance. This paper uses the Keepaway world as a case study and shows that models trained using ORLA not only perform better than those extracted from non-symbolic models but are also more robust. Moreover, ORLA is evaluated as a strategy discovery tool, finding a better solution than the expert strategy proposed by a related study.<\/jats:p>","DOI":"10.24963\/kr.2023\/53","type":"proceedings-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T22:27:47Z","timestamp":1690842467000},"page":"542-551","source":"Crossref","is-referenced-by-count":0,"title":["ORLA: Learning Explainable Argumentation Models"],"prefix":"10.24963","author":[{"given":"C\u00e1ndido","family":"Otero","sequence":"first","affiliation":[{"name":"Information and Computing Sciences, Utrecht University"}]},{"given":"Dennis","family":"Craandijk","sequence":"additional","affiliation":[{"name":"Information and Computing Sciences, Utrecht University"},{"name":"National Police Lab AI, Netherlands Police"}]},{"given":"Floris","family":"Bex","sequence":"additional","affiliation":[{"name":"Information and Computing Sciences, Utrecht University"},{"name":"Institute for Law, Technology and Society, Tilburg University"}]}],"member":"10584","event":{"number":"20","sponsor":["Artificial Intelligence Journal","Principles of Knowledge Representation and Reasoning Inc.","Academic College of Tel-Aviv","European Association for Artificial Intelligence","National Science Foundation"],"acronym":"KR-2023","name":"20th International Conference on Principles of Knowledge Representation and Reasoning {KR-2023}","start":{"date-parts":[[2023,9,2]]},"theme":"Artificial Intelligence","location":"Rhodes, Greece","end":{"date-parts":[[2023,9,8]]}},"container-title":["Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning"],"original-title":[],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T22:28:35Z","timestamp":1690842515000},"score":1,"resource":{"primary":{"URL":"https:\/\/proceedings.kr.org\/2023\/53"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/kr.2023\/53","relation":{},"subject":[],"published":{"date-parts":[[2023,9]]}}}