{"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/behavioural-cloning","name":"Behavioural cloning","slug":"behavioural-cloning","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":45,"papers_with_code":16,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/bdd-x","name":"BDD-X","full_name":"Berkeley Deep Drive-X (eXplanation)","num_papers_in_archive":47},{"url":"/dataset/cowese","name":"CoWeSe","full_name":"Corpus Web Salud Espanol","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/imitation-learning","name":"Imitation Learning"}],"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":45,"of":45,"of_with_code":16,"tagged_in_all":45,"counts":{"archive_papers_tagged":45,"with_a_code_link":16,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":45,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/a-divergence-minimization-perspective-on","slug":"a-divergence-minimization-perspective-on","title":"A Divergence Minimization Perspective on Imitation Learning Methods","date":"2019-11-06","arxiv_id":"1911.02256","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/a-divergence-minimization-perspective-on#ran","syntology_url":"https://syntology.ai/paper/1911.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02256"}},"official":{"repos":["KamyarGh/rl_swiss"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explorative-imitation-learning-a-path","slug":"explorative-imitation-learning-a-path","title":"Explorative Imitation Learning: A Path Signature Approach for Continuous Environments","date":"2024-07-05","arxiv_id":"2407.04856","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explorative-imitation-learning-a-path#ran","syntology_url":"https://syntology.ai/paper/2407.04856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04856"}},"official":{"repos":["NathanGavenski/CILO"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/self-supervised-adversarial-imitation","slug":"self-supervised-adversarial-imitation","title":"Self-Supervised Adversarial Imitation Learning","date":"2023-04-21","arxiv_id":"2304.10914","repositories_listed":2,"syntology":null},{"url":"/paper/action-advising-with-advice-imitation-in-deep","slug":"action-advising-with-advice-imitation-in-deep","title":"Action Advising with Advice Imitation in Deep Reinforcement Learning","date":"2021-04-17","arxiv_id":"2104.08441","repositories_listed":2,"syntology":null},{"url":"/paper/counter-strike-deathmatch-with-large-scale","slug":"counter-strike-deathmatch-with-large-scale","title":"Counter-Strike Deathmatch with Large-Scale Behavioural Cloning","date":"2021-04-09","arxiv_id":"2104.04258","repositories_listed":2,"syntology":null},{"url":"/paper/imitating-unknown-policies-via-exploration","slug":"imitating-unknown-policies-via-exploration","title":"Imitating Unknown Policies via Exploration","date":"2020-08-13","arxiv_id":"2008.05660","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imitating-unknown-policies-via-exploration#ran","syntology_url":"https://syntology.ai/paper/2008.05660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.05660"}},"official":{"repos":["NathanGavenski/IUPE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/augmented-behavioral-cloning-from-observation","slug":"augmented-behavioral-cloning-from-observation","title":"Augmented Behavioral Cloning from Observation","date":"2020-04-28","arxiv_id":"2004.13529","repositories_listed":2,"syntology":null},{"url":"/paper/improving-trust-estimation-in-human-robot","slug":"improving-trust-estimation-in-human-robot","title":"Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-grained Timescales","date":"2024-11-04","arxiv_id":"2411.01866","repositories_listed":1,"syntology":null},{"url":"/paper/evil-evolution-strategies-for-generalisable","slug":"evil-evolution-strategies-for-generalisable","title":"EvIL: Evolution Strategies for Generalisable Imitation Learning","date":"2024-06-15","arxiv_id":"2406.11905","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/evil-evolution-strategies-for-generalisable#ran","syntology_url":"https://syntology.ai/paper/2406.11905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11905"}},"official":{"repos":["SilviaSapora/evil"],"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/policy-improvement-using-language-feedback","slug":"policy-improvement-using-language-feedback","title":"Policy Improvement using Language Feedback Models","date":"2024-02-12","arxiv_id":"2402.07876","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-improvement-using-language-feedback#ran","syntology_url":"https://syntology.ai/paper/2402.07876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07876"}},"official":{"repos":["vzhong/language_feedback_models"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/oil-ad-an-anomaly-detection-framework-for","slug":"oil-ad-an-anomaly-detection-framework-for","title":"OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences","date":"2024-02-07","arxiv_id":"2402.04567","repositories_listed":1,"syntology":null},{"url":"/paper/balancing-policy-constraint-and-ensemble-size","slug":"balancing-policy-constraint-and-ensemble-size","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","date":"2023-03-26","arxiv_id":"2303.14716","repositories_listed":1,"syntology":null},{"url":"/paper/a-pragmatic-look-at-deep-imitation-learning","slug":"a-pragmatic-look-at-deep-imitation-learning","title":"A Pragmatic Look at Deep Imitation Learning","date":"2021-08-04","arxiv_id":"2108.01867","repositories_listed":1,"syntology":null},{"url":"/paper/playing-minecraft-with-behavioural-cloning","slug":"playing-minecraft-with-behavioural-cloning","title":"Playing Minecraft with Behavioural Cloning","date":"2020-05-07","arxiv_id":"2005.03374","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/playing-minecraft-with-behavioural-cloning#ran","syntology_url":"https://syntology.ai/paper/2005.03374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03374"}},"official":{"repos":["Miffyli/minecraft-bc"],"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/benchmarking-end-to-end-behavioural-cloning","slug":"benchmarking-end-to-end-behavioural-cloning","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","date":"2020-04-02","arxiv_id":"2004.00981","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attention-networks-reveal-the-rules-of","slug":"deep-attention-networks-reveal-the-rules-of","title":"Deep attention networks reveal the rules of collective motion in zebrafish","date":"2019-09-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"what-do-you-need-for-diverse-trajectory","title":"What Do You Need for Diverse Trajectory Stitching in Diffusion Planning?","date":"2025-05-23","arxiv_id":"2505.18083","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-time-policy-switching-for-offline","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","date":"2025-03-15","arxiv_id":"2503.12222","repositories_listed":0,"syntology":null},{"url":null,"slug":"problem-space-transformations-for","title":"Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning","date":"2024-11-06","arxiv_id":"2411.04056","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-to-online-reinforcement-learning-for","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","date":"2024-10-19","arxiv_id":"2410.14957","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-navigation-with-energy-based","title":"Vision-Language Navigation with Energy-Based Policy","date":"2024-10-18","arxiv_id":"2410.14250","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-vehicle-controllers-from-end-to","title":"Autonomous Vehicle Controllers From End-to-End Differentiable Simulation","date":"2024-09-12","arxiv_id":"2409.07965","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21713","title":"Social Learning through Interactions with Other Agents: A Survey","date":"2024-07-31","arxiv_id":"2407.21713","repositories_listed":0,"syntology":null},{"url":null,"slug":"closing-the-gap-optimizing-guidance-and","title":"Closing the gap: Optimizing Guidance and Control Networks through Neural ODEs","date":"2024-04-25","arxiv_id":"2404.16908","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-imitation-learning-for-automated-game","title":"Robust Imitation Learning for Automated Game Testing","date":"2024-01-09","arxiv_id":"2401.04572","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavioural-cloning-in-vizdoom","title":"Behavioural Cloning in VizDoom","date":"2024-01-08","arxiv_id":"2401.03993","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effectiveness-of-retrieval-alignment","title":"On the Effectiveness of Retrieval, Alignment, and Replay in Manipulation","date":"2023-12-19","arxiv_id":"2312.12345","repositories_listed":0,"syntology":null},{"url":null,"slug":"working-backwards-learning-to-place-by","title":"Working Backwards: Learning to Place by Picking","date":"2023-12-04","arxiv_id":"2312.02352","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-manipulation-network-roman-hybrid","title":"RObotic MAnipulation Network (ROMAN) $\\unicode{x2013}$ Hybrid Hierarchical Learning for Solving Complex Sequential Tasks","date":"2023-06-30","arxiv_id":"2307.00125","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavioral-cloning-via-search-in-embedded","title":"Behavioral Cloning via Search in Embedded Demonstration Dataset","date":"2023-06-15","arxiv_id":"2306.09082","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-imitation-learning","title":"Quantum Imitation Learning","date":"2023-04-04","arxiv_id":"2304.02480","repositories_listed":0,"syntology":null},{"url":null,"slug":"behaviour-discriminator-a-simple-data","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","date":"2023-01-27","arxiv_id":"2301.11734","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-trajectory-stitching-for-improved-1","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","date":"2022-12-08","arxiv_id":"2212.04280","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-td3-bc-relaxed-policy-constraint","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","date":"2022-11-21","arxiv_id":"2211.11802","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-trajectory-stitching-for-improved","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","date":"2022-11-21","arxiv_id":"2211.11603","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-theoretic-policy-extraction-from","title":"Information-Theoretic Policy Learning from Partial Observations with Fully Informed Decision Makers","date":"2022-04-04","arxiv_id":"2204.02350","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-behavioural-cloning-with-human","title":"Improving Behavioural Cloning with Human-Driven Dynamic Dataset Augmentation","date":"2022-01-19","arxiv_id":"2201.07719","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-cooperation-and-online-planning","title":"Learning Cooperation and Online Planning Through Simulation and Graph Convolutional Network","date":"2021-10-16","arxiv_id":"2110.08480","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-classify-and-imitate-trading","title":"Learning to Classify and Imitate Trading Agents in Continuous Double Auction Markets","date":"2021-10-04","arxiv_id":"2110.01325","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-lottery-tickets-and-minimal-task","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","date":"2021-05-04","arxiv_id":"2105.01648","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-reward-learning-for-offline","title":"Semi-supervised reward learning for offline reinforcement learning","date":"2020-12-12","arxiv_id":"2012.06899","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-reinforcement-learning-hands-on","title":"Offline Reinforcement Learning Hands-On","date":"2020-11-29","arxiv_id":"2011.14379","repositories_listed":0,"syntology":null},{"url":null,"slug":"safari-safe-and-active-robot-imitation","title":"SAFARI: Safe and Active Robot Imitation Learning with Imagination","date":"2020-11-18","arxiv_id":"2011.09586","repositories_listed":0,"syntology":null},{"url":null,"slug":"residual-learning-from-demonstration","title":"Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation","date":"2020-08-18","arxiv_id":"2008.07682","repositories_listed":0,"syntology":null},{"url":null,"slug":"newtonianvae-proportional-control-and-goal","title":"NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spaces","date":"2020-06-02","arxiv_id":"2006.01959","repositories_listed":0,"syntology":null}],"syntology_records":6,"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":6,"papers_where_code_ran_first_page":"/task/behavioural-cloning/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/behavioural-cloning/papers/ran/1","json":"/task/behavioural-cloning/papers/ran/1.json","rows":6}],"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":"525e5e9d080ed636b6a6d855e93d66ee63776236c7f394e4a1a96cb810e7bbc0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}