{"pk":29801,"title":"Investigating Simple Object Representations in Model-Free Deep ReinforcementLearning","subtitle":null,"abstract":"We explore the benefits of augmenting state-of-the-art model-free deep reinforcement learning with simple object representa-tions. Following the Frostbite challenge posited by Lake et al.(2017), we identify object representations as a critical cognitivecapacity lacking from current reinforcement learning agents.We discover that providing the Rainbow model (Hessel et al.,2018) with simple, feature-engineered object representationssubstantially boosts its performance on the Frostbite game fromAtari 2600. We then analyze the relative contributions of therepresentations of different types of objects, identify environ-ment states where these representations are most impactful, andexamine how these representations aid in generalizing to novelsituations.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"deep reinforcement learning; object representa-tions; model-free reinforcement learning; DQN."}],"section":"Poster Session 2","is_remote":true,"remote_url":"https://escholarship.org/uc/item/36c0g2mz","frozenauthors":[{"first_name":"Guy","middle_name":"","last_name":"Davidson","name_suffix":"","institution":"New York University","department":""},{"first_name":"Brenden","middle_name":"M.","last_name":"Lake","name_suffix":"","institution":"New York University","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2020-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/29801/galley/19655/download/"}]}