{"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/montezumas-revenge","name":"Montezuma's Revenge","slug":"montezumas-revenge","description_markdown":"Montezuma's Revenge is an ATARI 2600 Benchmark game that is known to be difficult to perform on for reinforcement learning algorithms. Solutions typically employ algorithms that incentivise environment exploration in different ways.\r\n\r\nFor the state-of-the art tables, please consult the parent Atari Games task.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Q-map](https://github.com/fabiopardo/qmap) )</span>","categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":61,"papers_with_code":31,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/montezuma-s-revenge-on-atari-2600-montezuma-s","slug":"montezuma-s-revenge-on-atari-2600-montezuma-s","dataset":"Atari 2600 Montezuma's Revenge","dataset_url":"/dataset/arcade-learning-environment","rows_in_archive":3,"metrics":["Average Return (NoOp)"],"first_row_in_archive_order":{"model":"Flare","paper_title":"Reinforcement Learning with Latent Flow","paper_url":"/paper/reinforcement-learning-with-latent-flow-1","paper_date":"2021-01-06","arxiv_id":"2101.01857","code_links":[{"title":"WendyShang/flare","url":"https://github.com/WendyShang/flare"},{"title":"WendyShang/dqn_zoo","url":"https://github.com/WendyShang/dqn_zoo"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}}}],"datasets":[{"url":"/dataset/arcade-learning-environment","name":"Arcade Learning Environment","full_name":"Arcade Learning Environment","num_papers_in_archive":366}],"subtasks":[],"parent_tasks":[{"url":"/task/atari-games","name":"Atari Games"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":61,"of":61,"of_with_code":31,"tagged_in_all":61,"counts":{"archive_papers_tagged":61,"with_a_code_link":31,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":61,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":4,"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"},"items":[{"url":"/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","repositories_listed":34,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","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"}},"official":null}},{"url":"/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","repositories_listed":22,"syntology":{"n":43,"n_ran":31,"n_constructed":12,"n_ran_checked":24,"n_instrument":7,"n_unverified":12,"n_honours":2,"n_violates":1,"n_no_contract":21,"n_pointer_only":16,"phrase":"31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified","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"}},"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"]}}},{"url":"/paper/hierarchical-deep-reinforcement-learning","slug":"hierarchical-deep-reinforcement-learning","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","date":"2016-04-20","arxiv_id":"1604.06057","repositories_listed":4,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"official":null}},{"url":"/paper/a-study-of-global-and-episodic-bonuses-for","slug":"a-study-of-global-and-episodic-bonuses-for","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","date":"2023-06-05","arxiv_id":"2306.03236","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/first-return-then-explore","slug":"first-return-then-explore","title":"First return, then explore","date":"2020-04-27","arxiv_id":"2004.12919","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/exploring-unknown-states-with-action-balance","slug":"exploring-unknown-states-with-action-balance","title":"Exploring Unknown States with Action Balance","date":"2020-03-10","arxiv_id":"2003.04518","repositories_listed":2,"syntology":null},{"url":"/paper/q-map-a-convolutional-approach-for-goal","slug":"q-map-a-convolutional-approach-for-goal","title":"Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks","date":"2018-10-06","arxiv_id":"1810.02927","repositories_listed":2,"syntology":null},{"url":"/paper/2505-10819","slug":"2505-10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","date":"2025-05-16","arxiv_id":"2505.10819","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-of-plasticity-loss-in-on-policy-deep","slug":"a-study-of-plasticity-loss-in-on-policy-deep","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19153","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-study-of-plasticity-loss-in-on-policy-deep#ran","syntology_url":"https://syntology.ai/paper/2405.19153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19153"}},"official":{"repos":["awjuliani/deep-rl-plasticity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-reinforcement-learning-models-is","slug":"fine-tuning-reinforcement-learning-models-is","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","date":"2024-02-05","arxiv_id":"2402.02868","repositories_listed":1,"syntology":null},{"url":"/paper/flipping-coins-to-estimate-pseudocounts-for","slug":"flipping-coins-to-estimate-pseudocounts-for","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","date":"2023-06-05","arxiv_id":"2306.03186","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/flipping-coins-to-estimate-pseudocounts-for#ran","syntology_url":"https://syntology.ai/paper/2306.03186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.03186"}},"official":{"repos":["samlobel/cfn"],"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"]}}},{"url":"/paper/redeeming-intrinsic-rewards-via-constrained","slug":"redeeming-intrinsic-rewards-via-constrained","title":"Redeeming Intrinsic Rewards via Constrained Optimization","date":"2022-11-14","arxiv_id":"2211.07627","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/redeeming-intrinsic-rewards-via-constrained#ran","syntology_url":"https://syntology.ai/paper/2211.07627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07627"}},"official":{"repos":["improbable-ai/eipo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hybrid-rl-using-both-offline-and-online-data","slug":"hybrid-rl-using-both-offline-and-online-data","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","date":"2022-10-13","arxiv_id":"2210.06718","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hybrid-rl-using-both-offline-and-online-data#ran","syntology_url":"https://syntology.ai/paper/2210.06718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06718"}},"official":{"repos":["yudasong/hyq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cell-free-latent-go-explore","slug":"cell-free-latent-go-explore","title":"Cell-Free Latent Go-Explore","date":"2022-08-31","arxiv_id":"2208.14928","repositories_listed":1,"syntology":null},{"url":"/paper/open-ended-reinforcement-learning-with-neural","slug":"open-ended-reinforcement-learning-with-neural","title":"Open-Ended Reinforcement Learning with Neural Reward Functions","date":"2022-02-16","arxiv_id":"2202.08266","repositories_listed":1,"syntology":null},{"url":"/paper/noveld-a-simple-yet-effective-exploration","slug":"noveld-a-simple-yet-effective-exploration","title":"NovelD: A Simple yet Effective Exploration Criterion","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-abstract-models-for-strategic","slug":"learning-abstract-models-for-strategic","title":"Learning Abstract Models for Strategic Exploration and Fast Reward Transfer","date":"2020-07-12","arxiv_id":"2007.05896","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-sensitive-learning-and-planning-1","slug":"uncertainty-sensitive-learning-and-planning-1","title":"Uncertainty-sensitive Learning and Planning with Ensembles","date":"2019-12-19","arxiv_id":"1912.09996","repositories_listed":1,"syntology":null},{"url":"/paper/deepsynth-program-synthesis-for-automatic","slug":"deepsynth-program-synthesis-for-automatic","title":"DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning","date":"2019-11-22","arxiv_id":"1911.10244","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-sensitive-learning-and-planning","slug":"uncertainty-sensitive-learning-and-planning","title":"Uncertainty - sensitive learning and planning with ensembles","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/combining-experience-replay-with-exploration","slug":"combining-experience-replay-with-exploration","title":"Combining Experience Replay with Exploration by Random Network Distillation","date":"2019-05-18","arxiv_id":"1905.07579","repositories_listed":1,"syntology":null},{"url":"/paper/using-natural-language-for-reward-shaping-in","slug":"using-natural-language-for-reward-shaping-in","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","date":"2019-03-05","arxiv_id":"1903.02020","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/using-natural-language-for-reward-shaping-in#ran","syntology_url":"https://syntology.ai/paper/1903.02020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02020"}},"official":null}},{"url":"/paper/empowerment-driven-exploration-using-mutual","slug":"empowerment-driven-exploration-using-mutual","title":"Empowerment-driven Exploration using Mutual Information Estimation","date":"2018-10-11","arxiv_id":"1810.05533","repositories_listed":1,"syntology":null},{"url":"/paper/playing-hard-exploration-games-by-watching","slug":"playing-hard-exploration-games-by-watching","title":"Playing hard exploration games by watching YouTube","date":"2018-05-29","arxiv_id":"1805.11592","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/playing-hard-exploration-games-by-watching#ran","syntology_url":"https://syntology.ai/paper/1805.11592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.11592"}},"official":null}},{"url":"/paper/feature-control-as-intrinsic-motivation-for","slug":"feature-control-as-intrinsic-motivation-for","title":"Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning","date":"2017-05-18","arxiv_id":"1705.06769","repositories_listed":1,"syntology":null},{"url":"/paper/beating-atari-with-natural-language-guided","slug":"beating-atari-with-natural-language-guided","title":"Beating Atari with Natural Language Guided Reinforcement Learning","date":"2017-04-18","arxiv_id":"1704.05539","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","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"}},"official":null}},{"url":"/paper/playing-atari-games-with-deep-reinforcement","slug":"playing-atari-games-with-deep-reinforcement","title":"Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay","date":"2016-07-18","arxiv_id":"1607.05077","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-count-based-exploration-and","slug":"unifying-count-based-exploration-and","title":"Unifying Count-Based Exploration and Intrinsic Motivation","date":"2016-06-06","arxiv_id":"1606.01868","repositories_listed":1,"syntology":null},{"url":null,"slug":"action-dependent-optimality-preserving-reward","title":"Action-Dependent Optimality-Preserving Reward Shaping","date":"2025-05-19","arxiv_id":"2505.12611","repositories_listed":0,"syntology":null},{"url":null,"slug":"int-hrl-towards-intention-based-hierarchical","title":"Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning","date":"2023-06-20","arxiv_id":"2306.11483","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-deep-reinforcement-learning-3","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","date":"2023-01-29","arxiv_id":"2301.12579","repositories_listed":0,"syntology":null},{"url":null,"slug":"curiosity-in-hindsight","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","date":"2022-11-18","arxiv_id":"2211.10515","repositories_listed":0,"syntology":null},{"url":null,"slug":"paused-agent-replay-refresh","title":"Paused Agent Replay Refresh","date":"2022-09-26","arxiv_id":"2209.13398","repositories_listed":0,"syntology":null},{"url":null,"slug":"gan-based-intrinsic-exploration-for-sample","title":"GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning","date":"2022-06-28","arxiv_id":"2206.14256","repositories_listed":0,"syntology":null},{"url":null,"slug":"parametrically-retargetable-decision-makers","title":"Parametrically Retargetable Decision-Makers Tend To Seek Power","date":"2022-06-27","arxiv_id":"2206.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-and-preventing-capacity-loss-in-1","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","date":"2022-04-20","arxiv_id":"2204.09560","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-exploration-for","title":"Generative Adversarial Exploration for Reinforcement Learning","date":"2022-01-27","arxiv_id":"2201.11685","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-by-random-network-distillation-1","title":"Exploration by Random Network Distillation","date":"2022-01-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"creativity-of-ai-automatic-symbolic-option","title":"Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning","date":"2021-12-18","arxiv_id":"2112.09836","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropic-desired-dynamics-for-intrinsic","title":"Entropic Desired Dynamics for Intrinsic Control","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-bonus-based-exploration-methods-in-the-1","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","date":"2021-09-22","arxiv_id":"2109.11052","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-providing-post-hoc-symbolic","title":"Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations","date":"2020-02-04","arxiv_id":"2002.01080","repositories_listed":0,"syntology":null},{"url":null,"slug":"mime-mutual-information-minimisation","title":"MIME: Mutual Information Minimisation Exploration","date":"2020-01-16","arxiv_id":"2001.05636","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-bonus-based-exploration-methods-in-the","title":"On Bonus Based Exploration Methods In The Arcade Learning Environment","date":"2020-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-bonus-based-exploration-methods","title":"Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment","date":"2019-08-06","arxiv_id":"1908.02388","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-exploration-with-self-imitation","title":"Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards","date":"2019-07-24","arxiv_id":"1907.10247","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-exploiting-multiple-subgoals-for","title":"Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning","date":"2019-05-13","arxiv_id":"1905.05180","repositories_listed":0,"syntology":null},{"url":null,"slug":"escape-room-a-configurable-testbed-for","title":"Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning","date":"2018-12-22","arxiv_id":"1812.09521","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-montezumas-revenge-from-a-single","title":"Learning Montezuma's Revenge from a Single Demonstration","date":"2018-12-08","arxiv_id":"1812.03381","repositories_listed":0,"syntology":null},{"url":"/paper/contingency-aware-exploration-in","slug":"contingency-aware-exploration-in","title":"Contingency-Aware Exploration in Reinforcement Learning","date":"2018-11-05","arxiv_id":"1811.01483","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-representations-in-model-free","title":"Learning Representations in Model-Free Hierarchical Reinforcement Learning","date":"2018-10-23","arxiv_id":"1810.10096","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-curiosity-search-intra-life-exploration","title":"Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problems","date":"2018-06-01","arxiv_id":"1806.00553","repositories_listed":0,"syntology":null},{"url":null,"slug":"observe-and-look-further-achieving-consistent","title":"Observe and Look Further: Achieving Consistent Performance on Atari","date":"2018-05-29","arxiv_id":"1805.11593","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-imitation-and-reinforcement","title":"Hierarchical Imitation and Reinforcement Learning","date":"2018-03-01","arxiv_id":"1803.00590","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-high-level-representations-from","title":"Learning High-level Representations from Demonstrations","date":"2018-02-19","arxiv_id":"1802.06604","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-in-feature-space-for","title":"Exploration in Feature Space for Reinforcement Learning","date":"2017-10-05","arxiv_id":"1710.02210","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-abstract-q-networks","title":"Deep Abstract Q-Networks","date":"2017-10-02","arxiv_id":"1710.00459","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}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/montezumas-revenge/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/montezumas-revenge/papers/ran/1","json":"/task/montezumas-revenge/papers/ran/1.json","rows":12}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"14b04984f8bd7abd432dade47728074995c4defe792a6059bd81f6f3ac09a7f9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}