{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unifying-count-based-exploration-and","title":"Unifying Count-Based Exploration and Intrinsic Motivation","arxiv_id":"1606.01868","date":"2016-06-06","proceeding":"NeurIPS 2016 12","authors":["Marc G. Bellemare","Sriram Srinivasan","Georg Ostrovski","Tom Schaul","David Saxton","Remi Munos"],"abstract":"We consider an agent's uncertainty about its environment and the problem of\ngeneralizing this uncertainty across observations. Specifically, we focus on\nthe problem of exploration in non-tabular reinforcement learning. Drawing\ninspiration from the intrinsic motivation literature, we use density models to\nmeasure uncertainty, and propose a novel algorithm for deriving a pseudo-count\nfrom an arbitrary density model. This technique enables us to generalize\ncount-based exploration algorithms to the non-tabular case. We apply our ideas\nto Atari 2600 games, providing sensible pseudo-counts from raw pixels. We\ntransform these pseudo-counts into intrinsic rewards and obtain significantly\nimproved exploration in a number of hard games, including the infamously\ndifficult Montezuma's Revenge.","url_abs":"http://arxiv.org/abs/1606.01868v2","url_pdf":"http://arxiv.org/pdf/1606.01868v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unifying-count-based-exploration-and","repo_url":"https://github.com/RLAgent/state-marginal-matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"montezumas-revenge","task_name":"Montezuma's Revenge"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"A3C-CTS","rank_in_archive_order":32,"of":59,"metrics":{"Score":"30.48"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"A3C-CTS","rank_in_archive_order":49,"of":53,"metrics":{"Score":"238.68"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"DDQN-PC","rank_in_archive_order":10,"of":50,"metrics":{"Score":"3459"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"A3C-CTS","rank_in_archive_order":23,"of":50,"metrics":{"Score":"273.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"A3C-CTS","rank_in_archive_order":46,"of":52,"metrics":{"Score":"99.32"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"A3C-CTS","rank_in_archive_order":50,"of":55,"metrics":{"Score":"0.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.01868","atlas_url":"https://app.syntology.ai/?focus=1606.01868","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}