{"pk":27244,"title":"Geometric Concept Acquisition in a Dueling Deep Q-Network","subtitle":null,"abstract":"Explaining how intelligent systems come to embody knowl-edge of deductive concepts through inductive learning is afundamental challenge of both cognitive science and artificialintelligence. We address this challenge by exploring how adeep reinforcement learning agent, occupying a setting simi-lar to those encountered by early-stage mathematical conceptlearners, comes to represent ideas such as rotation and trans-lation. We first train a Dueling Deep Q-Network on a shapesorting task requiring implicit knowledge of geometric proper-ties, then we query this network with classification and prefer-ence selection tasks. We demonstrate that scalar reinforcementprovides sufficient signal to learn representations of shape cat-egories. After training, the model shows a preference for moresymmetric shapes, which it can sort more quickly than lesssymmetric shapes, supporting the view symmetry preferencesmay be acquired from goal-directed experience.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Posters: Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/3v11228x","frozenauthors":[{"first_name":"Alex","middle_name":"","last_name":"Kuefler","name_suffix":"","institution":"Stanford University","department":""},{"first_name":"Mykel","middle_name":"J.","last_name":"Kochenderfer","name_suffix":"","institution":"Stanford University","department":""},{"first_name":"James","middle_name":"L.","last_name":"McClelland","name_suffix":"","institution":"Stanford University","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2017-01-01T13:00:00-05:00","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/27244/galley/16880/download/"}]}