{"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/imitation-learning/papers/ran/2","list_of":"/task/imitation-learning","task":"Imitation Learning","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"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 task or check it against the task'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.","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":234,"counts":{"archive_papers_tagged":2122,"with_a_code_link":691,"where_syntology_ran_a_sample":234,"not_listed_spam_title":0,"listed":2122,"listed_where_code_ran":234,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":191,"every_run_a_failure_of_syntologys_instrument":43,"listed_with_a_run_with_no_instrument_failure":191,"listed_every_run_a_failure_of_syntologys_instrument":43,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/imitation-learning/papers/ran/1","prev":"/task/imitation-learning/papers/ran/1","next":"/task/imitation-learning/papers/ran/3","papers":[{"url":"/paper/visual-imitation-learning-with-patch-rewards","slug":"visual-imitation-learning-with-patch-rewards","title":"Visual Imitation Learning with Patch Rewards","date":"2023-02-02","arxiv_id":"2302.00965","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/visual-imitation-learning-with-patch-rewards#ran","syntology_url":"https://syntology.ai/paper/2302.00965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00965"}},"official":{"repos":["sail-sg/patchail"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-imitation-learning-with-vector","slug":"hierarchical-imitation-learning-with-vector","title":"Hierarchical Imitation Learning with Vector Quantized Models","date":"2023-01-30","arxiv_id":"2301.12962","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":8,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-imitation-learning-with-vector#ran","syntology_url":"https://syntology.ai/paper/2301.12962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12962"}},"official":null}},{"url":"/paper/winning-solution-of-real-robot-challenge-iii","slug":"winning-solution-of-real-robot-challenge-iii","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","date":"2023-01-30","arxiv_id":"2301.13019","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/winning-solution-of-real-robot-challenge-iii#ran","syntology_url":"https://syntology.ai/paper/2301.13019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13019"}},"official":{"repos":["wq13552463699/real-robot-challenge-2022"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/orbit-a-unified-simulation-framework-for","slug":"orbit-a-unified-simulation-framework-for","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","date":"2023-01-10","arxiv_id":"2301.04195","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/orbit-a-unified-simulation-framework-for#ran","syntology_url":"https://syntology.ai/paper/2301.04195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.04195"}},"official":{"repos":["NVIDIA-Omniverse/Orbit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/discovering-latent-knowledge-in-language","slug":"discovering-latent-knowledge-in-language","title":"Discovering Latent Knowledge in Language Models Without Supervision","date":"2022-12-07","arxiv_id":"2212.03827","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/discovering-latent-knowledge-in-language#ran","syntology_url":"https://syntology.ai/paper/2212.03827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03827"}},"official":{"repos":["collin-burns/discovering_latent_knowledge"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-clean-imitation-learning","slug":"imitation-clean-imitation-learning","title":"imitation: Clean Imitation Learning Implementations","date":"2022-11-22","arxiv_id":"2211.11972","repositories_listed":2,"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":4,"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/imitation-clean-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2211.11972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11972"}},"official":{"repos":["HumanCompatibleAI/imitation"],"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":["listed","official"]}}},{"url":"/paper/plant-explainable-planning-transformers-via","slug":"plant-explainable-planning-transformers-via","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","date":"2022-10-25","arxiv_id":"2210.14222","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/plant-explainable-planning-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2210.14222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14222"}},"official":{"repos":["autonomousvision/plant"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/planning-for-sample-efficient-imitation","slug":"planning-for-sample-efficient-imitation","title":"Planning for Sample Efficient Imitation Learning","date":"2022-10-18","arxiv_id":"2210.09598","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":4,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/planning-for-sample-efficient-imitation#ran","syntology_url":"https://syntology.ai/paper/2210.09598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09598"}},"official":{"repos":["zhaohengyin/EfficientImitate"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-imitation-of-a-few-demonstrations-with","slug":"robust-imitation-of-a-few-demonstrations-with","title":"Robust Imitation of a Few Demonstrations with a Backwards Model","date":"2022-10-17","arxiv_id":"2210.09337","repositories_listed":0,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-imitation-of-a-few-demonstrations-with#ran","syntology_url":"https://syntology.ai/paper/2210.09337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09337"}},"official":null}},{"url":"/paper/frame-mining-a-free-lunch-for-learning","slug":"frame-mining-a-free-lunch-for-learning","title":"Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds","date":"2022-10-14","arxiv_id":"2210.07442","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/frame-mining-a-free-lunch-for-learning#ran","syntology_url":"https://syntology.ai/paper/2210.07442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07442"}},"official":{"repos":["xuanlinli17/corl_22_frame_mining"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-imitation-learning-for-urban","slug":"model-based-imitation-learning-for-urban","title":"Model-Based Imitation Learning for Urban Driving","date":"2022-10-14","arxiv_id":"2210.07729","repositories_listed":1,"syntology":{"n":23,"n_ran":21,"n_constructed":13,"n_ran_checked":13,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"21 ran (of which 13 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/model-based-imitation-learning-for-urban#ran","syntology_url":"https://syntology.ai/paper/2210.07729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07729"}},"official":{"repos":["wayveai/mile"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":13,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/markup-to-image-diffusion-models-with","slug":"markup-to-image-diffusion-models-with","title":"Markup-to-Image Diffusion Models with Scheduled Sampling","date":"2022-10-11","arxiv_id":"2210.05147","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/markup-to-image-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2210.05147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.05147"}},"official":{"repos":["da03/markup2im"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vima-general-robot-manipulation-with","slug":"vima-general-robot-manipulation-with","title":"VIMA: General Robot Manipulation with Multimodal Prompts","date":"2022-10-06","arxiv_id":"2210.03094","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vima-general-robot-manipulation-with#ran","syntology_url":"https://syntology.ai/paper/2210.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03094"}},"official":{"repos":["vimalabs/VIMABench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/discriminator-weighted-offline-imitation-1","slug":"discriminator-weighted-offline-imitation-1","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","date":"2022-07-20","arxiv_id":"2207.10050","repositories_listed":2,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 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; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/discriminator-weighted-offline-imitation-1#ran","syntology_url":"https://syntology.ai/paper/2207.10050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10050"}},"official":{"repos":["ryanxhr/dwbc"],"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/target-absent-human-attention","slug":"target-absent-human-attention","title":"Target-absent Human Attention","date":"2022-07-04","arxiv_id":"2207.01166","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/target-absent-human-attention#ran","syntology_url":"https://syntology.ai/paper/2207.01166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01166"}},"official":{"repos":["cvlab-stonybrook/target-absent-human-attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/webshop-towards-scalable-real-world-web","slug":"webshop-towards-scalable-real-world-web","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","date":"2022-07-04","arxiv_id":"2207.01206","repositories_listed":3,"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/webshop-towards-scalable-real-world-web#ran","syntology_url":"https://syntology.ai/paper/2207.01206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01206"}},"official":{"repos":["princeton-nlp/WebShop"],"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/video-pretraining-vpt-learning-to-act-by","slug":"video-pretraining-vpt-learning-to-act-by","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","date":"2022-06-23","arxiv_id":"2206.11795","repositories_listed":2,"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/video-pretraining-vpt-learning-to-act-by#ran","syntology_url":"https://syntology.ai/paper/2206.11795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11795"}},"official":{"repos":["openai/Video-Pre-Training"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/nocturne-a-scalable-driving-benchmark-for","slug":"nocturne-a-scalable-driving-benchmark-for","title":"Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world","date":"2022-06-20","arxiv_id":"2206.09889","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nocturne-a-scalable-driving-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2206.09889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09889"}},"official":{"repos":["facebookresearch/nocturne"],"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"]}}},{"url":"/paper/robust-imitation-learning-against-variations","slug":"robust-imitation-learning-against-variations","title":"Robust Imitation Learning against Variations in Environment Dynamics","date":"2022-06-19","arxiv_id":"2206.09314","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-imitation-learning-against-variations#ran","syntology_url":"https://syntology.ai/paper/2206.09314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09314"}},"official":{"repos":["jongseongchae/rime"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/silver-bullet-3d-at-maniskill-2021-learning","slug":"silver-bullet-3d-at-maniskill-2021-learning","title":"Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation","date":"2022-06-13","arxiv_id":"2206.06289","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":9,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":12,"phrase":"13 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/silver-bullet-3d-at-maniskill-2021-learning#ran","syntology_url":"https://syntology.ai/paper/2206.06289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06289"}},"official":{"repos":["caiqi/silver-bullet-3d"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":9,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/imitation-learning-via-differentiable-physics","slug":"imitation-learning-via-differentiable-physics","title":"Imitation Learning via Differentiable Physics","date":"2022-06-10","arxiv_id":"2206.04873","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imitation-learning-via-differentiable-physics#ran","syntology_url":"https://syntology.ai/paper/2206.04873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04873"}},"official":{"repos":["sail-sg/ild"],"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"]}}},{"url":"/paper/transfuser-imitation-with-transformer-based","slug":"transfuser-imitation-with-transformer-based","title":"TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving","date":"2022-05-31","arxiv_id":"2205.15997","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transfuser-imitation-with-transformer-based#ran","syntology_url":"https://syntology.ai/paper/2205.15997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15997"}},"official":{"repos":["autonomousvision/transfuser"],"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/tasil-taylor-series-imitation-learning","slug":"tasil-taylor-series-imitation-learning","title":"TaSIL: Taylor Series Imitation Learning","date":"2022-05-30","arxiv_id":"2205.14812","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tasil-taylor-series-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2205.14812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14812"}},"official":{"repos":["unstable-zeros/tasil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-empirical-investigation-of-representation","slug":"an-empirical-investigation-of-representation","title":"An Empirical Investigation of Representation Learning for Imitation","date":"2022-05-16","arxiv_id":"2205.07886","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-empirical-investigation-of-representation#ran","syntology_url":"https://syntology.ai/paper/2205.07886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.07886"}},"official":{"repos":["humancompatibleai/eirli","humancompatibleai/il-representations"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ase-large-scale-reusable-adversarial-skill","slug":"ase-large-scale-reusable-adversarial-skill","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","date":"2022-05-04","arxiv_id":"2205.01906","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ase-large-scale-reusable-adversarial-skill#ran","syntology_url":"https://syntology.ai/paper/2205.01906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01906"}},"official":null}},{"url":"/paper/king-generating-safety-critical-driving","slug":"king-generating-safety-critical-driving","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","date":"2022-04-28","arxiv_id":"2204.13683","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"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, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/king-generating-safety-critical-driving#ran","syntology_url":"https://syntology.ai/paper/2204.13683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13683"}},"official":{"repos":["autonomousvision/king"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-boltzmann-policy-distribution-accounting-1","slug":"the-boltzmann-policy-distribution-accounting-1","title":"The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models","date":"2022-04-22","arxiv_id":"2204.10759","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/the-boltzmann-policy-distribution-accounting-1#ran","syntology_url":"https://syntology.ai/paper/2204.10759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.10759"}},"official":{"repos":["cassidylaidlaw/boltzmann-policy-distribution"],"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/what-matters-in-language-conditioned-robotic","slug":"what-matters-in-language-conditioned-robotic","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","date":"2022-04-13","arxiv_id":"2204.06252","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/what-matters-in-language-conditioned-robotic#ran","syntology_url":"https://syntology.ai/paper/2204.06252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06252"}},"official":{"repos":["mees/hulc"],"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/why-exposure-bias-matters-an-imitation","slug":"why-exposure-bias-matters-an-imitation","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","date":"2022-04-03","arxiv_id":"2204.01171","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/why-exposure-bias-matters-an-imitation#ran","syntology_url":"https://syntology.ai/paper/2204.01171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01171"}},"official":{"repos":["kushalarora/quantifying_exposure_bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-visual-navigation-perspective-for-category","slug":"a-visual-navigation-perspective-for-category","title":"A Visual Navigation Perspective for Category-Level Object Pose Estimation","date":"2022-03-25","arxiv_id":"2203.13572","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-visual-navigation-perspective-for-category#ran","syntology_url":"https://syntology.ai/paper/2203.13572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13572"}},"official":{"repos":["wrld/visual_navigation_pose_estimation"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/teachable-reinforcement-learning-via-advice-1","slug":"teachable-reinforcement-learning-via-advice-1","title":"Teachable Reinforcement Learning via Advice Distillation","date":"2022-03-19","arxiv_id":"2203.11197","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/teachable-reinforcement-learning-via-advice-1#ran","syntology_url":"https://syntology.ai/paper/2203.11197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11197"}},"official":{"repos":["rll-research/teachable"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/motionaug-augmentation-with-physical","slug":"motionaug-augmentation-with-physical","title":"MotionAug: Augmentation with Physical Correction for Human Motion Prediction","date":"2022-03-17","arxiv_id":"2203.09116","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/motionaug-augmentation-with-physical#ran","syntology_url":"https://syntology.ai/paper/2203.09116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09116"}},"official":{"repos":["meaten/motionaug"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-the-gap-between-learning-in-discrete","slug":"bridging-the-gap-between-learning-in-discrete","title":"Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation","date":"2022-03-05","arxiv_id":"2203.02764","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-the-gap-between-learning-in-discrete#ran","syntology_url":"https://syntology.ai/paper/2203.02764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02764"}},"official":{"repos":["yiconghong/discrete-continuous-vln"],"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"]}}},{"url":"/paper/plan-your-target-and-learn-your-skills","slug":"plan-your-target-and-learn-your-skills","title":"Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization","date":"2022-03-04","arxiv_id":"2203.02214","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/plan-your-target-and-learn-your-skills#ran","syntology_url":"https://syntology.ai/paper/2203.02214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02214"}},"official":{"repos":["apexrl/DePO","apexrl/depo_ngsim"],"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/lobsdice-offline-imitation-learning-from","slug":"lobsdice-offline-imitation-learning-from","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","date":"2022-02-28","arxiv_id":"2202.13536","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/lobsdice-offline-imitation-learning-from#ran","syntology_url":"https://syntology.ai/paper/2202.13536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13536"}},"official":{"repos":["geon-hyeong/imitation-dice"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/revolver-continuous-evolutionary-models-for","slug":"revolver-continuous-evolutionary-models-for","title":"REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer","date":"2022-02-10","arxiv_id":"2202.05244","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":3,"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/revolver-continuous-evolutionary-models-for#ran","syntology_url":"https://syntology.ai/paper/2202.05244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05244"}},"official":{"repos":["xingyul/revolver"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-learning-by-state-only-distribution","slug":"imitation-learning-by-state-only-distribution","title":"Imitation Learning by State-Only Distribution Matching","date":"2022-02-09","arxiv_id":"2202.04332","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/imitation-learning-by-state-only-distribution#ran","syntology_url":"https://syntology.ai/paper/2202.04332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04332"}},"official":{"repos":["FeMa42/soil-tdm"],"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/bayesian-nonparametrics-for-offline-skill","slug":"bayesian-nonparametrics-for-offline-skill","title":"Bayesian Nonparametrics for Offline Skill Discovery","date":"2022-02-09","arxiv_id":"2202.04675","repositories_listed":1,"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":3,"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/bayesian-nonparametrics-for-offline-skill#ran","syntology_url":"https://syntology.ai/paper/2202.04675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04675"}},"official":{"repos":["layer6ai-labs/bnpo"],"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/smodice-versatile-offline-imitation-learning","slug":"smodice-versatile-offline-imitation-learning","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","date":"2022-02-04","arxiv_id":"2202.02433","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/smodice-versatile-offline-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2202.02433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02433"}},"official":{"repos":["jasonma2016/smodice"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pre-trained-language-models-for-interactive","slug":"pre-trained-language-models-for-interactive","title":"Pre-Trained Language Models for Interactive Decision-Making","date":"2022-02-03","arxiv_id":"2202.01771","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/pre-trained-language-models-for-interactive#ran","syntology_url":"https://syntology.ai/paper/2202.01771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01771"}},"official":null}},{"url":"/paper/imitation-learning-by-estimating-expertise-of","slug":"imitation-learning-by-estimating-expertise-of","title":"Imitation Learning by Estimating Expertise of Demonstrators","date":"2022-02-02","arxiv_id":"2202.01288","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/imitation-learning-by-estimating-expertise-of#ran","syntology_url":"https://syntology.ai/paper/2202.01288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01288"}},"official":{"repos":["stanford-iliad/ileed"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-guided-play-a-scheduled","slug":"learning-from-guided-play-a-scheduled","title":"Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning","date":"2021-12-16","arxiv_id":"2112.08932","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-from-guided-play-a-scheduled#ran","syntology_url":"https://syntology.ai/paper/2112.08932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08932"}},"official":{"repos":["utiasstars/lfgp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/combining-learning-from-human-feedback-and","slug":"combining-learning-from-human-feedback-and","title":"Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft","date":"2021-12-07","arxiv_id":"2112.03482","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/combining-learning-from-human-feedback-and#ran","syntology_url":"https://syntology.ai/paper/2112.03482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03482"}},"official":{"repos":["viniciusguigo/kairos_minerl_basalt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/calvin-a-benchmark-for-language-conditioned","slug":"calvin-a-benchmark-for-language-conditioned","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","date":"2021-12-06","arxiv_id":"2112.03227","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/calvin-a-benchmark-for-language-conditioned#ran","syntology_url":"https://syntology.ai/paper/2112.03227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03227"}},"official":{"repos":["mees/calvin"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-decision-transformer-for-offline","slug":"generalized-decision-transformer-for-offline","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","date":"2021-11-19","arxiv_id":"2111.10364","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":1,"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/generalized-decision-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2111.10364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10364"}},"official":{"repos":["frt03/generalized_dt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/lila-language-informed-latent-actions","slug":"lila-language-informed-latent-actions","title":"LILA: Language-Informed Latent Actions","date":"2021-11-05","arxiv_id":"2111.03205","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lila-language-informed-latent-actions#ran","syntology_url":"https://syntology.ai/paper/2111.03205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03205"}},"official":{"repos":["siddk/lila"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/rlds-an-ecosystem-to-generate-share-and-use","slug":"rlds-an-ecosystem-to-generate-share-and-use","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.02767","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/rlds-an-ecosystem-to-generate-share-and-use#ran","syntology_url":"https://syntology.ai/paper/2111.02767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02767"}},"official":{"repos":["google-research/rlds"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/curriculum-offline-imitation-learning","slug":"curriculum-offline-imitation-learning","title":"Curriculum Offline Imitation Learning","date":"2021-11-03","arxiv_id":"2111.02056","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/curriculum-offline-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2111.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02056"}},"official":{"repos":["apexrl/coil"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/object-aware-regularization-for-addressing","slug":"object-aware-regularization-for-addressing","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","date":"2021-10-27","arxiv_id":"2110.14118","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/object-aware-regularization-for-addressing#ran","syntology_url":"https://syntology.ai/paper/2110.14118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14118"}},"official":{"repos":["alinlab/oreo"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/starformer-transformer-with-state-action-1","slug":"starformer-transformer-with-state-action-1","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","date":"2021-10-12","arxiv_id":"2110.06206","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/starformer-transformer-with-state-action-1#ran","syntology_url":"https://syntology.ai/paper/2110.06206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06206"}},"official":{"repos":["elicassion/StARformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/film-following-instructions-in-language-with-1","slug":"film-following-instructions-in-language-with-1","title":"FILM: Following Instructions in Language with Modular Methods","date":"2021-10-12","arxiv_id":"2110.07342","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":1,"n_ran_checked":2,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":10,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/film-following-instructions-in-language-with-1#ran","syntology_url":"https://syntology.ai/paper/2110.07342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07342"}},"official":{"repos":["soyeonm/film"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/cross-domain-robot-imitation-with-invariant","slug":"cross-domain-robot-imitation-with-invariant","title":"Cross Domain Robot Imitation with Invariant Representation","date":"2021-09-13","arxiv_id":"2109.05940","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cross-domain-robot-imitation-with-invariant#ran","syntology_url":"https://syntology.ai/paper/2109.05940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05940"}},"official":{"repos":["zhaohengyin/irgail_example"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-urban-driving-by-imitating-a","slug":"end-to-end-urban-driving-by-imitating-a","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","date":"2021-08-18","arxiv_id":"2108.08265","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-urban-driving-by-imitating-a#ran","syntology_url":"https://syntology.ai/paper/2108.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08265"}},"official":{"repos":["zhejz/carla-roach"],"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/dexmv-imitation-learning-for-dexterous","slug":"dexmv-imitation-learning-for-dexterous","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","date":"2021-08-12","arxiv_id":"2108.05877","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dexmv-imitation-learning-for-dexterous#ran","syntology_url":"https://syntology.ai/paper/2108.05877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05877"}},"official":{"repos":["yzqin/dexmv-sim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-learning-by-reinforcement-learning","slug":"imitation-learning-by-reinforcement-learning","title":"Imitation Learning by Reinforcement Learning","date":"2021-08-10","arxiv_id":"2108.04763","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imitation-learning-by-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2108.04763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04763"}},"official":{"repos":["spotify-research/il-by-rl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/igibson-2-0-object-centric-simulation-for","slug":"igibson-2-0-object-centric-simulation-for","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","date":"2021-08-06","arxiv_id":"2108.03272","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/igibson-2-0-object-centric-simulation-for#ran","syntology_url":"https://syntology.ai/paper/2108.03272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03272"}},"official":null}},{"url":"/paper/what-matters-in-learning-from-offline-human","slug":"what-matters-in-learning-from-offline-human","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","date":"2021-08-06","arxiv_id":"2108.03298","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/what-matters-in-learning-from-offline-human#ran","syntology_url":"https://syntology.ai/paper/2108.03298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03298"}},"official":null}},{"url":"/paper/learning-a-large-neighborhood-search","slug":"learning-a-large-neighborhood-search","title":"Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs","date":"2021-07-21","arxiv_id":"2107.10201","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-a-large-neighborhood-search#ran","syntology_url":"https://syntology.ai/paper/2107.10201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.10201"}},"official":{"repos":["deepmind/neural_lns"],"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"]}}},{"url":"/paper/critic-guided-segmentation-of-rewarding","slug":"critic-guided-segmentation-of-rewarding","title":"Critic Guided Segmentation of Rewarding Objects in First-Person Views","date":"2021-07-20","arxiv_id":"2107.09540","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/critic-guided-segmentation-of-rewarding#ran","syntology_url":"https://syntology.ai/paper/2107.09540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09540"}},"official":null}},{"url":"/paper/scalable-perception-action-communication","slug":"scalable-perception-action-communication","title":"Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks","date":"2021-06-24","arxiv_id":"2106.13358","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scalable-perception-action-communication#ran","syntology_url":"https://syntology.ai/paper/2106.13358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13358"}},"official":{"repos":["VITA-Group/VGAI"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":5,"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":3,"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/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"}},"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"]}}},{"url":"/paper/cril-continual-robot-imitation-learning-via","slug":"cril-continual-robot-imitation-learning-via","title":"CRIL: Continual Robot Imitation Learning via Generative and Prediction Model","date":"2021-06-17","arxiv_id":"2106.09422","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cril-continual-robot-imitation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2106.09422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09422"}},"official":{"repos":["HeegerGao/CRIL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/solving-graph-based-public-good-games-with","slug":"solving-graph-based-public-good-games-with","title":"Solving Graph-based Public Good Games with Tree Search and Imitation Learning","date":"2021-06-12","arxiv_id":"2106.06762","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/solving-graph-based-public-good-games-with#ran","syntology_url":"https://syntology.ai/paper/2106.06762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06762"}},"official":{"repos":["victordarvariu/solving-graph-pgg"],"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/adversarial-option-aware-hierarchical","slug":"adversarial-option-aware-hierarchical","title":"Adversarial Option-Aware Hierarchical Imitation Learning","date":"2021-06-10","arxiv_id":"2106.05530","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarial-option-aware-hierarchical#ran","syntology_url":"https://syntology.ai/paper/2106.05530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05530"}},"official":{"repos":["id9502/Option-GAIL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-as-one-big-sequence","slug":"reinforcement-learning-as-one-big-sequence","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-03","arxiv_id":"2106.02039","repositories_listed":2,"syntology":{"n":28,"n_ran":23,"n_constructed":0,"n_ran_checked":22,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":21,"n_pointer_only":1,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/reinforcement-learning-as-one-big-sequence#ran","syntology_url":"https://syntology.ai/paper/2106.02039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02039"}},"official":{"repos":["JannerM/trajectory-transformer"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visitron-visual-semantics-aligned","slug":"visitron-visual-semantics-aligned","title":"VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator","date":"2021-05-25","arxiv_id":"2105.11589","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visitron-visual-semantics-aligned#ran","syntology_url":"https://syntology.ai/paper/2105.11589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11589"}},"official":{"repos":["alexa/visitron"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-fusion-transformer-for-end-to-end","slug":"multi-modal-fusion-transformer-for-end-to-end","title":"Multi-Modal Fusion Transformer for End-to-End Autonomous Driving","date":"2021-04-19","arxiv_id":"2104.09224","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":7,"n_ran_checked":8,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/multi-modal-fusion-transformer-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.09224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09224"}},"official":{"repos":["autonomousvision/transfuser"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-from-imperfect-demonstrations-from","slug":"learning-from-imperfect-demonstrations-from","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","date":"2021-03-10","arxiv_id":"2103.05910","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/learning-from-imperfect-demonstrations-from#ran","syntology_url":"https://syntology.ai/paper/2103.05910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05910"}},"official":null}},{"url":"/paper/proof-artifact-co-training-for-theorem","slug":"proof-artifact-co-training-for-theorem","title":"Proof Artifact Co-training for Theorem Proving with Language Models","date":"2021-02-11","arxiv_id":"2102.06203","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/proof-artifact-co-training-for-theorem#ran","syntology_url":"https://syntology.ai/paper/2102.06203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.06203"}},"official":{"repos":["jasonrute/lean-proof-recording-public","jasonrute/lean_proof_recording","jesse-michael-han/lean-step-public"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-policy-learning-with-routines","slug":"augmenting-policy-learning-with-routines","title":"Augmenting Policy Learning with Routines Discovered from a Single Demonstration","date":"2020-12-23","arxiv_id":"2012.12469","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-policy-learning-with-routines#ran","syntology_url":"https://syntology.ai/paper/2012.12469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12469"}},"official":{"repos":["sjtuytc/-AAAI21-RoutineAugmentedPolicyLearning-RAPL-","sjtuytc/AAAI21-RoutineAugmentedPolicyLearning"],"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"]}}},{"url":"/paper/policy-supervectors-general-characterization","slug":"policy-supervectors-general-characterization","title":"General Characterization of Agents by States they Visit","date":"2020-12-02","arxiv_id":"2012.01244","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/policy-supervectors-general-characterization#ran","syntology_url":"https://syntology.ai/paper/2012.01244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.01244"}},"official":{"repos":["Miffyli/policy-supervectors"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/derail-diagnostic-environments-for-reward-and","slug":"derail-diagnostic-environments-for-reward-and","title":"DERAIL: Diagnostic Environments for Reward And Imitation Learning","date":"2020-12-02","arxiv_id":"2012.01365","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/derail-diagnostic-environments-for-reward-and#ran","syntology_url":"https://syntology.ai/paper/2012.01365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.01365"}},"official":{"repos":["HumanCompatibleAI/derail","HumanCompatibleAI/seals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-magical-benchmark-for-robust-imitation","slug":"the-magical-benchmark-for-robust-imitation","title":"The MAGICAL Benchmark for Robust Imitation","date":"2020-11-01","arxiv_id":"2011.00401","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-magical-benchmark-for-robust-imitation#ran","syntology_url":"https://syntology.ai/paper/2011.00401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00401"}},"official":{"repos":["qxcv/magical"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/f-gail-learning-f-divergence-for-generative","slug":"f-gail-learning-f-divergence-for-generative","title":"$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning","date":"2020-10-02","arxiv_id":"2010.01207","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/f-gail-learning-f-divergence-for-generative#ran","syntology_url":"https://syntology.ai/paper/2010.01207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01207"}},"official":{"repos":["fGAIL3456/fGAIL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-social-reinforcement-learning","slug":"multi-agent-social-reinforcement-learning","title":"Emergent Social Learning via Multi-agent Reinforcement Learning","date":"2020-10-01","arxiv_id":"2010.00581","repositories_listed":0,"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/multi-agent-social-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2010.00581","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00581"}},"official":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/non-adversarial-imitation-learning-and-its","slug":"non-adversarial-imitation-learning-and-its","title":"Non-Adversarial Imitation Learning and its Connections to Adversarial Methods","date":"2020-08-08","arxiv_id":"2008.03525","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/non-adversarial-imitation-learning-and-its#ran","syntology_url":"https://syntology.ai/paper/2008.03525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.03525"}},"official":{"repos":["OlegArenz/O-NAIL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trajgail-generating-urban-trajectories-using","slug":"trajgail-generating-urban-trajectories-using","title":"TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning","date":"2020-07-28","arxiv_id":"2007.14189","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trajgail-generating-urban-trajectories-using#ran","syntology_url":"https://syntology.ai/paper/2007.14189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14189"}},"official":{"repos":["benchoi93/TrajGAIL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-robust-optimization-for-imitation","slug":"bayesian-robust-optimization-for-imitation","title":"Bayesian Robust Optimization for Imitation Learning","date":"2020-07-24","arxiv_id":"2007.12315","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bayesian-robust-optimization-for-imitation#ran","syntology_url":"https://syntology.ai/paper/2007.12315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12315"}},"official":{"repos":["dsbrown1331/broil"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/babyai-1-1","slug":"babyai-1-1","title":"BabyAI 1.1","date":"2020-07-24","arxiv_id":"2007.12770","repositories_listed":3,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/babyai-1-1#ran","syntology_url":"https://syntology.ai/paper/2007.12770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12770"}},"official":{"repos":["mila-iqia/babyai"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/policy-learning-with-partial-observation-and","slug":"policy-learning-with-partial-observation-and","title":"Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling","date":"2020-07-07","arxiv_id":"2007.03155","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/policy-learning-with-partial-observation-and#ran","syntology_url":"https://syntology.ai/paper/2007.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03155"}},"official":{"repos":["keisuke198619/PO-MC-DHVRNN"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/strictly-batch-imitation-learning-by-energy","slug":"strictly-batch-imitation-learning-by-energy","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","date":"2020-06-25","arxiv_id":"2006.14154","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":5,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":1,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/strictly-batch-imitation-learning-by-energy#ran","syntology_url":"https://syntology.ai/paper/2006.14154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14154"}},"official":{"repos":["vanderschaarlab/mlforhealthlabpub"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/aligning-time-series-on-incomparable-spaces","slug":"aligning-time-series-on-incomparable-spaces","title":"Aligning Time Series on Incomparable Spaces","date":"2020-06-22","arxiv_id":"2006.12648","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-time-series-on-incomparable-spaces#ran","syntology_url":"https://syntology.ai/paper/2006.12648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12648"}},"official":{"repos":["samcohen16/Aligning-Time-Series"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-imitation-learning-via-generalized-lower","slug":"self-imitation-learning-via-generalized-lower","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","date":"2020-06-12","arxiv_id":"2006.07442","repositories_listed":0,"syntology":{"n":20,"n_ran":16,"n_constructed":4,"n_ran_checked":13,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":11,"phrase":"16 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/self-imitation-learning-via-generalized-lower#ran","syntology_url":"https://syntology.ai/paper/2006.07442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07442"}},"official":null}},{"url":"/paper/babywalk-going-farther-in-vision-and-language","slug":"babywalk-going-farther-in-vision-and-language","title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps","date":"2020-05-10","arxiv_id":"2005.04625","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/babywalk-going-farther-in-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2005.04625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04625"}},"official":{"repos":["Sha-Lab/babywalk"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-imitation-game-for-learning-semantic","slug":"an-imitation-game-for-learning-semantic","title":"An Imitation Game for Learning Semantic Parsers from User Interaction","date":"2020-05-02","arxiv_id":"2005.00689","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-imitation-game-for-learning-semantic#ran","syntology_url":"https://syntology.ai/paper/2005.00689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00689"}},"official":{"repos":["sunlab-osu/MISP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/energy-based-imitation-learning","slug":"energy-based-imitation-learning","title":"Energy-Based Imitation Learning","date":"2020-04-20","arxiv_id":"2004.09395","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/energy-based-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2004.09395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.09395"}},"official":{"repos":["apexrl/EBIL-torch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-sparse-rewarded-tasks-from-sub","slug":"learning-sparse-rewarded-tasks-from-sub","title":"Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations","date":"2020-04-01","arxiv_id":"2004.00530","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"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: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-sparse-rewarded-tasks-from-sub#ran","syntology_url":"https://syntology.ai/paper/2004.00530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00530"}},"official":null}},{"url":"/paper/modeling-3d-shapes-by-reinforcement-learning","slug":"modeling-3d-shapes-by-reinforcement-learning","title":"Modeling 3D Shapes by Reinforcement Learning","date":"2020-03-27","arxiv_id":"2003.12397","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modeling-3d-shapes-by-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2003.12397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.12397"}},"official":null}},{"url":"/paper/sparse-graphical-memory-for-robust-planning","slug":"sparse-graphical-memory-for-robust-planning","title":"Sparse Graphical Memory for Robust Planning","date":"2020-03-13","arxiv_id":"2003.06417","repositories_listed":1,"syntology":{"n":13,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/sparse-graphical-memory-for-robust-planning#ran","syntology_url":"https://syntology.ai/paper/2003.06417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06417"}},"official":{"repos":["scottemmons/sgm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/the-minerl-competition-on-sample-efficient-1","slug":"the-minerl-competition-on-sample-efficient-1","title":"Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning","date":"2020-03-10","arxiv_id":"2003.05012","repositories_listed":0,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-minerl-competition-on-sample-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2003.05012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05012"}},"official":null}},{"url":"/paper/state-only-imitation-with-transition-dynamics-1","slug":"state-only-imitation-with-transition-dynamics-1","title":"State-only Imitation with Transition Dynamics Mismatch","date":"2020-02-27","arxiv_id":"2002.11879","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/state-only-imitation-with-transition-dynamics-1#ran","syntology_url":"https://syntology.ai/paper/2002.11879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11879"}},"official":{"repos":["tgangwani/RL-Indirect-imitation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-imitation-learning-via-fast-bayesian","slug":"safe-imitation-learning-via-fast-bayesian","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","date":"2020-02-21","arxiv_id":"2002.09089","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/safe-imitation-learning-via-fast-bayesian#ran","syntology_url":"https://syntology.ai/paper/2002.09089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09089"}},"official":{"repos":["dsbrown1331/bayesianrex"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["community","official"]}}},{"url":"/paper/estimating-qss-with-deep-deterministic","slug":"estimating-qss-with-deep-deterministic","title":"Estimating Q(s,s') with Deep Deterministic Dynamics Gradients","date":"2020-02-21","arxiv_id":"2002.09505","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/estimating-qss-with-deep-deterministic#ran","syntology_url":"https://syntology.ai/paper/2002.09505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09505"}},"official":null}},{"url":"/paper/parameterizing-branch-and-bound-search-trees","slug":"parameterizing-branch-and-bound-search-trees","title":"Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies","date":"2020-02-12","arxiv_id":"2002.05120","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/parameterizing-branch-and-bound-search-trees#ran","syntology_url":"https://syntology.ai/paper/2002.05120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05120"}},"official":{"repos":["ds4dm/branch-search-trees"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-interactions-modeling-with-1","slug":"multi-agent-interactions-modeling-with-1","title":"Multi-Agent Interactions Modeling with Correlated Policies","date":"2020-01-04","arxiv_id":"2001.03415","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":1,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"n_honours":5,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/multi-agent-interactions-modeling-with-1#ran","syntology_url":"https://syntology.ai/paper/2001.03415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.03415"}},"official":{"repos":["apexrl/CoDAIL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/reward-conditioned-policies","slug":"reward-conditioned-policies","title":"Reward-Conditioned Policies","date":"2019-12-31","arxiv_id":"1912.13465","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reward-conditioned-policies#ran","syntology_url":"https://syntology.ai/paper/1912.13465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.13465"}},"official":null}},{"url":"/paper/third-person-visual-imitation-learning-via-1","slug":"third-person-visual-imitation-learning-via-1","title":"Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller","date":"2019-11-21","arxiv_id":"1911.09676","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/third-person-visual-imitation-learning-via-1#ran","syntology_url":"https://syntology.ai/paper/1911.09676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09676"}},"official":{"repos":["pathak22/hierarchical-imitation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/bail-best-action-imitation-learning-for-batch-1","slug":"bail-best-action-imitation-learning-for-batch-1","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","date":"2019-10-27","arxiv_id":"1910.12179","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bail-best-action-imitation-learning-for-batch-1#ran","syntology_url":"https://syntology.ai/paper/1910.12179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12179"}},"official":{"repos":["lanyavik/BAIL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"defe30e387f20b7a5b77518eab9eaf4f724e1f17e238f2a0b039ac9e17ddeb98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}