{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":16,"of":16,"tagged_in_all":45,"items":[{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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","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","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","title":"Imitating Unknown Policies via Exploration","date":"2020-08-13","arxiv_id":"2008.05660","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/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","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","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_unverified":0,"n_pointer_only":3}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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","title":"Playing Minecraft with Behavioural Cloning","date":"2020-05-07","arxiv_id":"2005.03374","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","title":"Deep attention networks reveal the rules of collective motion in zebrafish","date":"2019-09-13","arxiv_id":null,"repositories_listed":1,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}