{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/atari-games/papers/7","list_of":"/task/atari-games","task":"Atari Games","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":7,"rows_per_page":100,"rows":[601,625],"of":625,"counts":{"archive_papers_tagged":625,"with_a_code_link":313,"where_syntology_ran_a_sample":118,"not_listed_spam_title":0,"listed":625,"listed_where_code_ran":118,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":21,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/atari-games","prev":"/task/atari-games/papers/6","next":null,"papers":[{"url":null,"slug":"atari-games-and-intel-processors","title":"Atari games and Intel processors","date":"2017-05-19","arxiv_id":"1705.06936","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-recurrence-and-eligibility","title":"Investigating Recurrence and Eligibility Traces in Deep Q-Networks","date":"2017-04-18","arxiv_id":"1704.05495","repositories_listed":0,"syntology":null},{"url":"/paper/the-reactor-a-fast-and-sample-efficient-actor","slug":"the-reactor-a-fast-and-sample-efficient-actor","title":"The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning","date":"2017-04-15","arxiv_id":"1704.04651","repositories_listed":0,"syntology":null},{"url":null,"slug":"micro-objective-learning-accelerating-deep","title":"Micro-Objective Learning : Accelerating Deep Reinforcement Learning through the Discovery of Continuous Subgoals","date":"2017-03-11","arxiv_id":"1703.03933","repositories_listed":0,"syntology":null},{"url":null,"slug":"tactics-of-adversarial-attack-on-deep","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","date":"2017-03-08","arxiv_id":"1703.06748","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-meta-learning-by-parallel-algorithm","title":"Online Meta-learning by Parallel Algorithm Competition","date":"2017-02-24","arxiv_id":"1702.07490","repositories_listed":0,"syntology":null},{"url":"/paper/sigmoid-weighted-linear-units-for-neural","slug":"sigmoid-weighted-linear-units-for-neural","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","date":"2017-02-10","arxiv_id":"1702.03118","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-predict-where-to-look-in","title":"Learning to predict where to look in interactive environments using deep recurrent q-learning","date":"2016-12-17","arxiv_id":"1612.05753","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-learning-approach-for-joint-video","title":"A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games","date":"2016-11-21","arxiv_id":"1611.07078","repositories_listed":0,"syntology":null},{"url":null,"slug":"averaged-dqn-variance-reduction-and","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","date":"2016-11-07","arxiv_id":"1611.01929","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-policy-gradient-and-q-learning","title":"Combining policy gradient and Q-learning","date":"2016-11-05","arxiv_id":"1611.01626","repositories_listed":0,"syntology":null},{"url":null,"slug":"combating-reinforcement-learnings-sisyphean","title":"Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear","date":"2016-11-03","arxiv_id":"1611.01211","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-with-macro","title":"Deep Reinforcement Learning With Macro-Actions","date":"2016-06-15","arxiv_id":"1606.04615","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategic-attentive-writer-for-learning-macro","title":"Strategic Attentive Writer for Learning Macro-Actions","date":"2016-06-15","arxiv_id":"1606.04695","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-frame-skip-deep-q-network","title":"Dynamic Frame skip Deep Q Network","date":"2016-05-17","arxiv_id":"1605.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-reward-design-to-improve","title":"Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games","date":"2016-04-24","arxiv_id":"1604.07095","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurohex-a-deep-q-learning-hex-agent","title":"Neurohex: A Deep Q-learning Hex Agent","date":"2016-04-24","arxiv_id":"1604.07097","repositories_listed":0,"syntology":null},{"url":"/paper/learning-values-across-many-orders-of","slug":"learning-values-across-many-orders-of","title":"Learning values across many orders of magnitude","date":"2016-02-24","arxiv_id":"1602.07714","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-visual-concepts-with","title":"Understanding Visual Concepts with Continuation Learning","date":"2016-02-22","arxiv_id":"1602.06822","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mathematical-theory-of-deep-convolutional","title":"A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction","date":"2015-12-19","arxiv_id":"1512.06293","repositories_listed":0,"syntology":null},{"url":null,"slug":"reuse-of-neural-modules-for-general-video","title":"Reuse of Neural Modules for General Video Game Playing","date":"2015-12-04","arxiv_id":"1512.01537","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-real-time-atari-game-play","title":"Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-learning-algorithms-on-the","title":"A Comparison of learning algorithms on the Arcade Learning Environment","date":"2014-10-31","arxiv_id":"1410.8620","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-autoregressive-networks","title":"Deep AutoRegressive Networks","date":"2013-10-31","arxiv_id":"1310.8499","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-based-linear-value-function","title":"Sketch-Based Linear Value Function Approximation","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"a872b5e11870638f1865131d4f12406919142a8a83972c64dab308ea4b02a7ac","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}