{"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/deep-exploration-via-bootstrapped-dqn","title":"Deep Exploration via Bootstrapped DQN","arxiv_id":"1602.04621","date":"2016-02-15","proceeding":"NeurIPS 2016 12","authors":["Ian Osband","Charles Blundell","Alexander Pritzel","Benjamin Van Roy"],"abstract":"Efficient exploration in complex environments remains a major challenge for\nreinforcement learning. We propose bootstrapped DQN, a simple algorithm that\nexplores in a computationally and statistically efficient manner through use of\nrandomized value functions. Unlike dithering strategies such as epsilon-greedy\nexploration, bootstrapped DQN carries out temporally-extended (or deep)\nexploration; this can lead to exponentially faster learning. We demonstrate\nthese benefits in complex stochastic MDPs and in the large-scale Arcade\nLearning Environment. Bootstrapped DQN substantially improves learning times\nand performance across most Atari games.","url_abs":"http://arxiv.org/abs/1602.04621v3","url_pdf":"http://arxiv.org/pdf/1602.04621v3.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":"deep-exploration-via-bootstrapped-dqn","repo_url":"https://github.com/NervanaSystems/coach","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-exploration-via-bootstrapped-dqn","repo_url":"https://github.com/johannah/bootstrap_dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-exploration-via-bootstrapped-dqn","repo_url":"https://github.com/mrahtz/learning-from-human-preferences","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"deep-exploration-via-bootstrapped-dqn","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-exploration-via-bootstrapped-dqn","repo_url":"https://github.com/tensorflow/models/tree/master/research/deep_contextual_bandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-exploration-via-bootstrapped-dqn","repo_url":"https://github.com/yaringal/HeteroscedasticDropoutUncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"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":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"Bootstrapped DQN","rank_in_archive_order":28,"of":49,"metrics":{"Score":"2436.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"Bootstrapped DQN","rank_in_archive_order":21,"of":48,"metrics":{"Score":"1272.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-assault","task":"Atari Games","dataset":"Atari 2600 Assault","model":"Bootstrapped DQN","rank_in_archive_order":21,"of":45,"metrics":{"Score":"8047.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asterix","task":"Atari Games","dataset":"Atari 2600 Asterix","model":"Bootstrapped DQN","rank_in_archive_order":27,"of":49,"metrics":{"Score":"19713.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-asteroids","task":"Atari Games","dataset":"Atari 2600 Asteroids","model":"Bootstrapped DQN","rank_in_archive_order":38,"of":43,"metrics":{"Score":"1032"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-atlantis","task":"Atari Games","dataset":"Atari 2600 Atlantis","model":"Bootstrapped DQN","rank_in_archive_order":11,"of":42,"metrics":{"Score":"994500"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bank-heist","task":"Atari Games","dataset":"Atari 2600 Bank Heist","model":"Bootstrapped DQN","rank_in_archive_order":18,"of":45,"metrics":{"Score":"1208"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-battle-zone","task":"Atari Games","dataset":"Atari 2600 Battle Zone","model":"Bootstrapped DQN","rank_in_archive_order":17,"of":47,"metrics":{"Score":"38666.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-beam-rider","task":"Atari Games","dataset":"Atari 2600 Beam Rider","model":"Bootstrapped DQN","rank_in_archive_order":17,"of":49,"metrics":{"Score":"23429.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-bowling","task":"Atari Games","dataset":"Atari 2600 Bowling","model":"Bootstrapped DQN","rank_in_archive_order":24,"of":44,"metrics":{"Score":"60.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-boxing","task":"Atari Games","dataset":"Atari 2600 Boxing","model":"Bootstrapped DQN","rank_in_archive_order":27,"of":45,"metrics":{"Score":"93.2"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-breakout","task":"Atari Games","dataset":"Atari 2600 Breakout","model":"Bootstrapped DQN","rank_in_archive_order":5,"of":58,"metrics":{"Score":"855"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-centipede","task":"Atari Games","dataset":"Atari 2600 Centipede","model":"Bootstrapped DQN","rank_in_archive_order":33,"of":45,"metrics":{"Score":"4553.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-chopper-command","task":"Atari Games","dataset":"Atari 2600 Chopper Command","model":"Bootstrapped DQN","rank_in_archive_order":35,"of":45,"metrics":{"Score":"4100"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"Bootstrapped DQN","rank_in_archive_order":21,"of":49,"metrics":{"Score":"137925.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-demon-attack","task":"Atari Games","dataset":"Atari 2600 Demon Attack","model":"Bootstrapped DQN","rank_in_archive_order":20,"of":46,"metrics":{"Score":"82610"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-double-dunk","task":"Atari Games","dataset":"Atari 2600 Double Dunk","model":"Bootstrapped DQN","rank_in_archive_order":17,"of":43,"metrics":{"Score":"3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"Bootstrapped DQN","rank_in_archive_order":24,"of":48,"metrics":{"Score":"1591"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-fishing-derby","task":"Atari Games","dataset":"Atari 2600 Fishing Derby","model":"Bootstrapped DQN","rank_in_archive_order":25,"of":44,"metrics":{"Score":"26"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-freeway","task":"Atari Games","dataset":"Atari 2600 Freeway","model":"Bootstrapped DQN","rank_in_archive_order":11,"of":59,"metrics":{"Score":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"Bootstrapped DQN","rank_in_archive_order":31,"of":53,"metrics":{"Score":"2181.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gopher","task":"Atari Games","dataset":"Atari 2600 Gopher","model":"Bootstrapped DQN","rank_in_archive_order":24,"of":43,"metrics":{"Score":"17438.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-gravitar","task":"Atari Games","dataset":"Atari 2600 Gravitar","model":"Bootstrapped DQN","rank_in_archive_order":46,"of":53,"metrics":{"Score":"286.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-hero","task":"Atari Games","dataset":"Atari 2600 HERO","model":"Bootstrapped DQN","rank_in_archive_order":26,"of":44,"metrics":{"Score":"21021.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ice-hockey","task":"Atari Games","dataset":"Atari 2600 Ice Hockey","model":"Bootstrapped DQN","rank_in_archive_order":36,"of":43,"metrics":{"Score":"-1.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-james-bond","task":"Atari Games","dataset":"Atari 2600 James Bond","model":"Bootstrapped DQN","rank_in_archive_order":19,"of":45,"metrics":{"Score":"1663.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kangaroo","task":"Atari Games","dataset":"Atari 2600 Kangaroo","model":"Bootstrapped DQN","rank_in_archive_order":7,"of":47,"metrics":{"Score":"14862.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"Bootstrapped DQN","rank_in_archive_order":26,"of":45,"metrics":{"Score":"8627.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-kung-fu-master","task":"Atari Games","dataset":"Atari 2600 Kung-Fu Master","model":"Bootstrapped DQN","rank_in_archive_order":24,"of":43,"metrics":{"Score":"36733.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-montezumas-revenge","task":"Atari Games","dataset":"Atari 2600 Montezuma's Revenge","model":"Bootstrapped DQN","rank_in_archive_order":26,"of":50,"metrics":{"Score":"100"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"Bootstrapped DQN","rank_in_archive_order":28,"of":47,"metrics":{"Score":"2983.3"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-name-this-game","task":"Atari Games","dataset":"Atari 2600 Name This Game","model":"Bootstrapped DQN","rank_in_archive_order":25,"of":43,"metrics":{"Score":"11501.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-pong","task":"Atari Games","dataset":"Atari 2600 Pong","model":"Bootstrapped DQN","rank_in_archive_order":20,"of":52,"metrics":{"Score":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-private-eye","task":"Atari Games","dataset":"Atari 2600 Private Eye","model":"Bootstrapped DQN","rank_in_archive_order":20,"of":52,"metrics":{"Score":"1812.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"Bootstrapped DQN","rank_in_archive_order":27,"of":57,"metrics":{"Score":"15092.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-river-raid","task":"Atari Games","dataset":"Atari 2600 River Raid","model":"Bootstrapped DQN","rank_in_archive_order":23,"of":41,"metrics":{"Score":"12845"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-road-runner","task":"Atari Games","dataset":"Atari 2600 Road Runner","model":"Bootstrapped DQN","rank_in_archive_order":26,"of":44,"metrics":{"Score":"51500"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-robotank","task":"Atari Games","dataset":"Atari 2600 Robotank","model":"Bootstrapped DQN","rank_in_archive_order":12,"of":42,"metrics":{"Score":"66.6"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"Bootstrapped DQN","rank_in_archive_order":23,"of":57,"metrics":{"Score":"9083.1"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-space-invaders","task":"Atari Games","dataset":"Atari 2600 Space Invaders","model":"Bootstrapped DQN","rank_in_archive_order":28,"of":55,"metrics":{"Score":"2893"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-star-gunner","task":"Atari Games","dataset":"Atari 2600 Star Gunner","model":"Bootstrapped DQN","rank_in_archive_order":30,"of":43,"metrics":{"Score":"55725"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tennis","task":"Atari Games","dataset":"Atari 2600 Tennis","model":"Bootstrapped DQN","rank_in_archive_order":23,"of":43,"metrics":{"Score":"0"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-time-pilot","task":"Atari Games","dataset":"Atari 2600 Time Pilot","model":"Bootstrapped DQN","rank_in_archive_order":25,"of":44,"metrics":{"Score":"9079.4"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-tutankham","task":"Atari Games","dataset":"Atari 2600 Tutankham","model":"Bootstrapped DQN","rank_in_archive_order":22,"of":44,"metrics":{"Score":"214.8"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-up-and-down","task":"Atari Games","dataset":"Atari 2600 Up and Down","model":"Bootstrapped DQN","rank_in_archive_order":25,"of":44,"metrics":{"Score":"26231"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-venture","task":"Atari Games","dataset":"Atari 2600 Venture","model":"Bootstrapped DQN","rank_in_archive_order":27,"of":55,"metrics":{"Score":"212.5"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-video-pinball","task":"Atari Games","dataset":"Atari 2600 Video Pinball","model":"Bootstrapped DQN","rank_in_archive_order":9,"of":42,"metrics":{"Score":"811610"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-wizard-of-wor","task":"Atari Games","dataset":"Atari 2600 Wizard of Wor","model":"Bootstrapped DQN","rank_in_archive_order":28,"of":41,"metrics":{"Score":"6804.7"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-zaxxon","task":"Atari Games","dataset":"Atari 2600 Zaxxon","model":"Bootstrapped DQN","rank_in_archive_order":22,"of":41,"metrics":{"Score":"11491.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.04621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.04621"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/johannah/bootstrap_dqn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaringal/HeteroscedasticDropoutUncertainty","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mrahtz/learning-from-human-preferences","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/deep_contextual_bandits","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NervanaSystems/coach","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"f1cb6f95361db966","entry":"rolling_average","repo":"johannah/bootstrap_dqn","repo_kind":"listed","path":"run_bootstrap.py","file_url":"https://github.com/johannah/bootstrap_dqn/blob/HEAD/run_bootstrap.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f1cb6f95361db966"}},{"code_sha256_prefix":"a667ce6b07647d3d","entry":"ptlearn","repo":"johannah/bootstrap_dqn","repo_kind":"listed","path":"run_bootstrap.py","file_url":"https://github.com/johannah/bootstrap_dqn/blob/HEAD/run_bootstrap.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a667ce6b07647d3d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}