{"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":"/dataset/arcade-learning-environment/papers/ran/1","list_of":"/dataset/arcade-learning-environment","dataset":"Arcade Learning Environment","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,35],"of":35,"counts":{"papers_with_a_benchmark_row":66,"with_a_code_link":56,"where_syntology_ran_a_sample":35,"not_listed_spam_title":0,"listed":66,"listed_where_code_ran":35,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":26,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":26,"listed_every_run_a_failure_of_syntologys_instrument":9,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/arcade-learning-environment/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/iq-learn-inverse-soft-q-learning-for","slug":"iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","rows_on_this_dataset":4,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}}}},{"paper":"/paper/decision-transformer-reinforcement-learning","slug":"decision-transformer-reinforcement-learning","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","date":"2021-06-02","arxiv_id":"2106.01345","rows_on_this_dataset":4,"code_links":20,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":26,"samples_ran":17,"samples_constructed":10,"samples_ran_checked":13,"samples_ran_instrument_failed":4,"samples_unverified":9,"pointer_only_for_licence":8,"official":{"repos":["kzl/decision-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/decision-transformer-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.01345","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01345"}}}},{"paper":"/paper/recurrent-rational-networks","slug":"recurrent-rational-networks","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","date":"2021-02-18","arxiv_id":"2102.09407","rows_on_this_dataset":26,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":6,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["ml-research/rational_activations","ml-research/rational_rl","ml-research/rational_sl","k4ntz/activation-functions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recurrent-rational-networks#ran","syntology_url":"https://syntology.ai/paper/2102.09407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09407"}}}},{"paper":"/paper/reinforcement-learning-with-latent-flow-1","slug":"reinforcement-learning-with-latent-flow-1","title":"Reinforcement Learning with Latent Flow","date":"2021-01-06","arxiv_id":"2101.01857","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["WendyShang/flare","WendyShang/dqn_zoo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reinforcement-learning-with-latent-flow-1#ran","syntology_url":"https://syntology.ai/paper/2101.01857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.01857"}}}},{"paper":"/paper/mastering-atari-with-discrete-world-models-1","slug":"mastering-atari-with-discrete-world-models-1","title":"Mastering Atari with Discrete World Models","date":"2020-10-05","arxiv_id":"2010.02193","rows_on_this_dataset":50,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":11,"samples_constructed":1,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["danijar/dreamerv2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mastering-atari-with-discrete-world-models-1#ran","syntology_url":"https://syntology.ai/paper/2010.02193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02193"}}}},{"paper":"/paper/munchausen-reinforcement-learning","slug":"munchausen-reinforcement-learning","title":"Munchausen Reinforcement Learning","date":"2020-07-28","arxiv_id":"2007.14430","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":22,"samples_ran":12,"samples_constructed":11,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":10,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/munchausen-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2007.14430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14430"}}}},{"paper":"/paper/first-return-then-explore","slug":"first-return-then-explore","title":"First return, then explore","date":"2020-04-27","arxiv_id":"2004.12919","rows_on_this_dataset":10,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["uber-research/go-explore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/first-return-then-explore#ran","syntology_url":"https://syntology.ai/paper/2004.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12919"}}}},{"paper":"/paper/curl-contrastive-unsupervised-representations","slug":"curl-contrastive-unsupervised-representations","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","date":"2020-04-08","arxiv_id":"2004.04136","rows_on_this_dataset":24,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":5,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["MishaLaskin/curl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/curl-contrastive-unsupervised-representations#ran","syntology_url":"https://syntology.ai/paper/2004.04136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04136"}}}},{"paper":"/paper/agent57-outperforming-the-atari-human","slug":"agent57-outperforming-the-atari-human","title":"Agent57: Outperforming the Atari Human Benchmark","date":"2020-03-30","arxiv_id":"2003.13350","rows_on_this_dataset":51,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/agent57-outperforming-the-atari-human#ran","syntology_url":"https://syntology.ai/paper/2003.13350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13350"}}}},{"paper":"/paper/mastering-atari-go-chess-and-shogi-by","slug":"mastering-atari-go-chess-and-shogi-by","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","date":"2019-11-19","arxiv_id":"1911.08265","rows_on_this_dataset":51,"code_links":18,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":64,"samples_ran":43,"samples_constructed":36,"samples_ran_checked":43,"samples_ran_instrument_failed":0,"samples_unverified":21,"pointer_only_for_licence":62,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mastering-atari-go-chess-and-shogi-by#ran","syntology_url":"https://syntology.ai/paper/1911.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08265"}}}},{"paper":"/paper/fully-parameterized-quantile-function-for","slug":"fully-parameterized-quantile-function-for","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","date":"2019-11-05","arxiv_id":"1911.02140","rows_on_this_dataset":23,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fully-parameterized-quantile-function-for#ran","syntology_url":"https://syntology.ai/paper/1911.02140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02140"}}}},{"paper":"/paper/soft-actor-critic-for-discrete-action","slug":"soft-actor-critic-for-discrete-action","title":"Soft Actor-Critic for Discrete Action Settings","date":"2019-10-16","arxiv_id":"1910.07207","rows_on_this_dataset":18,"code_links":13,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":18,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":3,"official":{"repos":["p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/soft-actor-critic-for-discrete-action#ran","syntology_url":"https://syntology.ai/paper/1910.07207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07207"}}}},{"paper":"/paper/recurrent-independent-mechanisms","slug":"recurrent-independent-mechanisms","title":"Recurrent Independent Mechanisms","date":"2019-09-24","arxiv_id":"1909.10893","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":20,"samples_ran":14,"samples_constructed":9,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":20,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/recurrent-independent-mechanisms#ran","syntology_url":"https://syntology.ai/paper/1909.10893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.10893"}}}},{"paper":"/paper/go-explore-a-new-approach-for-hard","slug":"go-explore-a-new-approach-for-hard","title":"Go-Explore: a New Approach for Hard-Exploration Problems","date":"2019-01-30","arxiv_id":"1901.10995","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/go-explore-a-new-approach-for-hard#ran","syntology_url":"https://syntology.ai/paper/1901.10995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10995"}}}},{"paper":"/paper/exploration-by-random-network-distillation","slug":"exploration-by-random-network-distillation","title":"Exploration by Random Network Distillation","date":"2018-10-30","arxiv_id":"1810.12894","rows_on_this_dataset":5,"code_links":22,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":43,"samples_ran":31,"samples_constructed":12,"samples_ran_checked":24,"samples_ran_instrument_failed":7,"samples_unverified":12,"pointer_only_for_licence":16,"official":{"repos":["openai/random-network-distillation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploration-by-random-network-distillation#ran","syntology_url":"https://syntology.ai/paper/1810.12894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12894"}}}},{"paper":"/paper/large-scale-study-of-curiosity-driven","slug":"large-scale-study-of-curiosity-driven","title":"Large-Scale Study of Curiosity-Driven Learning","date":"2018-08-13","arxiv_id":"1808.04355","rows_on_this_dataset":5,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["openai/large-scale-curiosity"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/large-scale-study-of-curiosity-driven#ran","syntology_url":"https://syntology.ai/paper/1808.04355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.04355"}}}},{"paper":"/paper/count-based-exploration-with-the-successor","slug":"count-based-exploration-with-the-successor","title":"Count-Based Exploration with the Successor Representation","date":"2018-07-31","arxiv_id":"1807.11622","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["mcmachado/count_based_exploration_sr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/count-based-exploration-with-the-successor#ran","syntology_url":"https://syntology.ai/paper/1807.11622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11622"}}}},{"paper":"/paper/rudder-return-decomposition-for-delayed","slug":"rudder-return-decomposition-for-delayed","title":"RUDDER: Return Decomposition for Delayed Rewards","date":"2018-06-20","arxiv_id":"1806.07857","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":9,"official":{"repos":["ml-jku/baselines-rudder","ml-jku/rudder"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rudder-return-decomposition-for-delayed#ran","syntology_url":"https://syntology.ai/paper/1806.07857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07857"}}}},{"paper":"/paper/self-imitation-learning","slug":"self-imitation-learning","title":"Self-Imitation Learning","date":"2018-06-14","arxiv_id":"1806.05635","rows_on_this_dataset":45,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":3,"official":{"repos":["junhyukoh/self-imitation-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1806.05635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05635"}}}},{"paper":"/paper/evolving-simple-programs-for-playing-atari","slug":"evolving-simple-programs-for-playing-atari","title":"Evolving simple programs for playing Atari games","date":"2018-06-14","arxiv_id":"1806.05695","rows_on_this_dataset":50,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evolving-simple-programs-for-playing-atari#ran","syntology_url":"https://syntology.ai/paper/1806.05695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05695"}}}},{"paper":"/paper/implicit-quantile-networks-for-distributional","slug":"implicit-quantile-networks-for-distributional","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","date":"2018-06-14","arxiv_id":"1806.06923","rows_on_this_dataset":51,"code_links":19,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/implicit-quantile-networks-for-distributional#ran","syntology_url":"https://syntology.ai/paper/1806.06923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.06923"}}}},{"paper":"/paper/distributed-prioritized-experience-replay","slug":"distributed-prioritized-experience-replay","title":"Distributed Prioritized Experience Replay","date":"2018-03-02","arxiv_id":"1803.00933","rows_on_this_dataset":51,"code_links":15,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distributed-prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1803.00933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.00933"}}}},{"paper":"/paper/impala-scalable-distributed-deep-rl-with","slug":"impala-scalable-distributed-deep-rl-with","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","date":"2018-02-05","arxiv_id":"1802.01561","rows_on_this_dataset":52,"code_links":24,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":34,"samples_ran":16,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":6,"samples_unverified":18,"pointer_only_for_licence":3,"official":{"repos":["deepmind/scalable_agent"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/impala-scalable-distributed-deep-rl-with#ran","syntology_url":"https://syntology.ai/paper/1802.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01561"}}}},{"paper":"/paper/distributional-reinforcement-learning-with-1","slug":"distributional-reinforcement-learning-with-1","title":"Distributional Reinforcement Learning with Quantile Regression","date":"2017-10-27","arxiv_id":"1710.10044","rows_on_this_dataset":51,"code_links":17,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distributional-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/1710.10044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10044"}}}},{"paper":"/paper/rainbow-combining-improvements-in-deep","slug":"rainbow-combining-improvements-in-deep","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","date":"2017-10-06","arxiv_id":"1710.02298","rows_on_this_dataset":4,"code_links":34,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rainbow-combining-improvements-in-deep#ran","syntology_url":"https://syntology.ai/paper/1710.02298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.02298"}}}},{"paper":"/paper/noisy-networks-for-exploration","slug":"noisy-networks-for-exploration","title":"Noisy Networks for Exploration","date":"2017-06-30","arxiv_id":"1706.10295","rows_on_this_dataset":48,"code_links":15,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/noisy-networks-for-exploration#ran","syntology_url":"https://syntology.ai/paper/1706.10295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.10295"}}}},{"paper":"/paper/evolution-strategies-as-a-scalable","slug":"evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","arxiv_id":"1703.03864","rows_on_this_dataset":41,"code_links":23,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":29,"samples_ran":16,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":5,"samples_unverified":13,"pointer_only_for_licence":2,"official":{"repos":["openai/evolution-strategies-starter"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/evolution-strategies-as-a-scalable#ran","syntology_url":"https://syntology.ai/paper/1703.03864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03864"}}}},{"paper":"/paper/count-based-exploration-with-neural-density","slug":"count-based-exploration-with-neural-density","title":"Count-Based Exploration with Neural Density Models","date":"2017-03-03","arxiv_id":"1703.01310","rows_on_this_dataset":9,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/count-based-exploration-with-neural-density#ran","syntology_url":"https://syntology.ai/paper/1703.01310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01310"}}}},{"paper":"/paper/deep-exploration-via-bootstrapped-dqn","slug":"deep-exploration-via-bootstrapped-dqn","title":"Deep Exploration via Bootstrapped DQN","date":"2016-02-15","arxiv_id":"1602.04621","rows_on_this_dataset":45,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-exploration-via-bootstrapped-dqn#ran","syntology_url":"https://syntology.ai/paper/1602.04621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.04621"}}}},{"paper":"/paper/asynchronous-methods-for-deep-reinforcement","slug":"asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","arxiv_id":"1602.01783","rows_on_this_dataset":138,"code_links":70,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":95,"samples_ran":60,"samples_constructed":20,"samples_ran_checked":51,"samples_ran_instrument_failed":9,"samples_unverified":35,"pointer_only_for_licence":20,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/asynchronous-methods-for-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1602.01783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.01783"}}}},{"paper":"/paper/dueling-network-architectures-for-deep","slug":"dueling-network-architectures-for-deep","title":"Dueling Network Architectures for Deep Reinforcement Learning","date":"2015-11-20","arxiv_id":"1511.06581","rows_on_this_dataset":185,"code_links":73,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":7,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dueling-network-architectures-for-deep#ran","syntology_url":"https://syntology.ai/paper/1511.06581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06581"}}}},{"paper":"/paper/prioritized-experience-replay","slug":"prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","arxiv_id":"1511.05952","rows_on_this_dataset":91,"code_links":77,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":111,"samples_ran":80,"samples_constructed":62,"samples_ran_checked":72,"samples_ran_instrument_failed":8,"samples_unverified":31,"pointer_only_for_licence":43,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prioritized-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1511.05952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05952"}}}},{"paper":"/paper/deep-reinforcement-learning-with-double-q","slug":"deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","arxiv_id":"1509.06461","rows_on_this_dataset":183,"code_links":97,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":106,"samples_ran":56,"samples_constructed":38,"samples_ran_checked":55,"samples_ran_instrument_failed":1,"samples_unverified":50,"pointer_only_for_licence":57,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-reinforcement-learning-with-double-q#ran","syntology_url":"https://syntology.ai/paper/1509.06461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.06461"}}}},{"paper":"/paper/playing-atari-with-deep-reinforcement","slug":"playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","arxiv_id":"1312.5602","rows_on_this_dataset":6,"code_links":112,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":117,"samples_ran":64,"samples_constructed":24,"samples_ran_checked":46,"samples_ran_instrument_failed":18,"samples_unverified":53,"pointer_only_for_licence":56,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/playing-atari-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1312.5602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1312.5602"}}}},{"paper":"/paper/the-arcade-learning-environment-an-evaluation","slug":"the-arcade-learning-environment-an-evaluation","title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","date":"2012-07-19","arxiv_id":"1207.4708","rows_on_this_dataset":98,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}}}}],"record_sha256":"5432ecfa9c06c8ab27d2f8134d7a791dfa62a738379d82379909a232f4139581","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}