{"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/6","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":6,"pages_in_order":22,"rows_per_page":100,"rows":[501,600],"of":2122,"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","prev":"/task/imitation-learning/papers/5","next":"/task/imitation-learning/papers/7","papers":[{"url":"/paper/brain-inspired-deep-imitation-learning-for","slug":"brain-inspired-deep-imitation-learning-for","title":"Brain-Inspired Deep Imitation Learning for Autonomous Driving Systems","date":"2021-07-30","arxiv_id":"2107.14654","repositories_listed":1,"syntology":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/vision-based-autonomous-car-racing-using-deep","slug":"vision-based-autonomous-car-racing-using-deep","title":"Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning","date":"2021-07-18","arxiv_id":"2107.08325","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-mixture-density-networks-learning","slug":"adversarial-mixture-density-networks-learning","title":"Adversarial Mixture Density Networks: Learning to Drive Safely from Collision Data","date":"2021-07-09","arxiv_id":"2107.04485","repositories_listed":1,"syntology":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/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/causal-navigation-by-continuous-time-neural","slug":"causal-navigation-by-continuous-time-neural","title":"Causal Navigation by Continuous-time Neural Networks","date":"2021-06-15","arxiv_id":"2106.08314","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-as-one-big-sequence-1","slug":"reinforcement-learning-as-one-big-sequence-1","title":"Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/mitigating-covariate-shift-in-imitation","slug":"mitigating-covariate-shift-in-imitation","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","date":"2021-06-06","arxiv_id":"2106.03207","repositories_listed":1,"syntology":null},{"url":"/paper/what-matters-for-adversarial-imitation","slug":"what-matters-for-adversarial-imitation","title":"What Matters for Adversarial Imitation Learning?","date":"2021-06-01","arxiv_id":"2106.00672","repositories_listed":1,"syntology":null},{"url":"/paper/provable-representation-learning-for","slug":"provable-representation-learning-for","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","date":"2021-05-26","arxiv_id":"2105.12272","repositories_listed":1,"syntology":null},{"url":"/paper/from-motor-control-to-team-play-in-simulated","slug":"from-motor-control-to-team-play-in-simulated","title":"From Motor Control to Team Play in Simulated Humanoid Football","date":"2021-05-25","arxiv_id":"2105.12196","repositories_listed":1,"syntology":null},{"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/mitigating-covariate-shift-in-imitation-1","slug":"mitigating-covariate-shift-in-imitation-1","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage","date":"2021-05-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/most-multi-source-domain-adaptation-via","slug":"most-multi-source-domain-adaptation-via","title":"MOST: Multi-Source Domain Adaptation via Optimal Transport for Student-Teacher Learning","date":"2021-05-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/seeing-all-the-angles-learning-multiview","slug":"seeing-all-the-angles-learning-multiview","title":"Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations","date":"2021-04-28","arxiv_id":"2104.13907","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-grasping-policies-for-human-in-the","slug":"end-to-end-grasping-policies-for-human-in-the","title":"End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning","date":"2021-04-26","arxiv_id":"2104.12842","repositories_listed":1,"syntology":null},{"url":"/paper/an-adversarial-imitation-click-model-for","slug":"an-adversarial-imitation-click-model-for","title":"An Adversarial Imitation Click Model for Information Retrieval","date":"2021-04-13","arxiv_id":"2104.06077","repositories_listed":1,"syntology":null},{"url":"/paper/no-need-for-interactions-robust-model-based","slug":"no-need-for-interactions-robust-model-based","title":"No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE","date":"2021-04-03","arxiv_id":"2104.01390","repositories_listed":1,"syntology":null},{"url":"/paper/contrastively-learning-visual-attention-as","slug":"contrastively-learning-visual-attention-as","title":"Contrastively Learning Visual Attention as Affordance Cues from Demonstrations for Robotic Grasping","date":"2021-04-02","arxiv_id":"2104.00878","repositories_listed":1,"syntology":null},{"url":"/paper/icurb-imitation-learning-based-detection-of","slug":"icurb-imitation-learning-based-detection-of","title":"iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving","date":"2021-03-31","arxiv_id":"2103.17118","repositories_listed":1,"syntology":null},{"url":"/paper/topo-boundary-a-benchmark-dataset-on","slug":"topo-boundary-a-benchmark-dataset-on","title":"Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving","date":"2021-03-31","arxiv_id":"2103.17119","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-imitation-learning-with","slug":"adversarial-imitation-learning-with","title":"Adversarial Imitation Learning with Trajectorial Augmentation and Correction","date":"2021-03-25","arxiv_id":"2103.13887","repositories_listed":1,"syntology":null},{"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/domain-robust-visual-imitation-learning-with-1","slug":"domain-robust-visual-imitation-learning-with-1","title":"Domain-Robust Visual Imitation Learning with Mutual Information Constraints","date":"2021-03-08","arxiv_id":"2103.05079","repositories_listed":1,"syntology":null},{"url":"/paper/gaze-informed-multi-objective-imitation","slug":"gaze-informed-multi-objective-imitation","title":"Imitation Learning with Human Eye Gaze via Multi-Objective Prediction","date":"2021-02-25","arxiv_id":"2102.13008","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/gaze-informed-multi-objective-imitation#ran","syntology_url":"https://syntology.ai/paper/2102.13008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.13008"}},"official":{"repos":["ravikt/gril"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/off-policy-imitation-learning-from-1","slug":"off-policy-imitation-learning-from-1","title":"Off-Policy Imitation Learning from Observations","date":"2021-02-25","arxiv_id":"2102.13185","repositories_listed":1,"syntology":null},{"url":"/paper/optimism-is-all-you-need-model-based","slug":"optimism-is-all-you-need-model-based","title":"MobILE: Model-Based Imitation Learning From Observation Alone","date":"2021-02-22","arxiv_id":"2102.10769","repositories_listed":1,"syntology":null},{"url":"/paper/intrinsically-motivated-open-ended-multi-task","slug":"intrinsically-motivated-open-ended-multi-task","title":"Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy","date":"2021-02-19","arxiv_id":"2102.09854","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-learning-from-activity","slug":"interactive-learning-from-activity","title":"Interactive Learning from Activity Description","date":"2021-02-13","arxiv_id":"2102.07024","repositories_listed":1,"syntology":null},{"url":"/paper/learning-structural-edits-via-incremental-1","slug":"learning-structural-edits-via-incremental-1","title":"Learning Structural Edits via Incremental Tree Transformations","date":"2021-01-28","arxiv_id":"2101.12087","repositories_listed":1,"syntology":null},{"url":"/paper/mpc-mpnet-model-predictive-motion-planning","slug":"mpc-mpnet-model-predictive-motion-planning","title":"MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic Constraints","date":"2021-01-17","arxiv_id":"2101.06798","repositories_listed":1,"syntology":null},{"url":"/paper/robust-asymmetric-learning-in-pomdps","slug":"robust-asymmetric-learning-in-pomdps","title":"Robust Asymmetric Learning in POMDPs","date":"2020-12-31","arxiv_id":"2012.15566","repositories_listed":1,"syntology":null},{"url":"/paper/learning-cross-domain-correspondence-for-1","slug":"learning-cross-domain-correspondence-for-1","title":"Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency","date":"2020-12-17","arxiv_id":"2012.09811","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-with-stability-and-safety","slug":"imitation-learning-with-stability-and-safety","title":"Imitation Learning with Stability and Safety Guarantees","date":"2020-12-16","arxiv_id":"2012.09293","repositories_listed":1,"syntology":null},{"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/tstarbot-x-an-open-sourced-and-comprehensive","slug":"tstarbot-x-an-open-sourced-and-comprehensive","title":"TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game","date":"2020-11-27","arxiv_id":"2011.13729","repositories_listed":1,"syntology":null},{"url":"/paper/episodic-self-imitation-learning-with","slug":"episodic-self-imitation-learning-with","title":"Episodic Self-Imitation Learning with Hindsight","date":"2020-11-26","arxiv_id":"2011.13467","repositories_listed":1,"syntology":null},{"url":"/paper/cdt-cascading-decision-trees-for-explainable-1","slug":"cdt-cascading-decision-trees-for-explainable-1","title":"CDT: Cascading Decision Trees for Explainable Reinforcement Learning","date":"2020-11-15","arxiv_id":"2011.07553","repositories_listed":1,"syntology":null},{"url":"/paper/editor-an-edit-based-transformer-with","slug":"editor-an-edit-based-transformer-with","title":"EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints","date":"2020-11-13","arxiv_id":"2011.06868","repositories_listed":1,"syntology":null},{"url":"/paper/f-irl-inverse-reinforcement-learning-via","slug":"f-irl-inverse-reinforcement-learning-via","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","date":"2020-11-09","arxiv_id":"2011.04709","repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-planning-for-autonomous-vehicles","slug":"trajectory-planning-for-autonomous-vehicles","title":"Trajectory Planning for Autonomous Vehicles Using Hierarchical Reinforcement Learning","date":"2020-11-09","arxiv_id":"2011.04752","repositories_listed":1,"syntology":null},{"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/language-conditioned-imitation-learning-for","slug":"language-conditioned-imitation-learning-for","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","date":"2020-10-22","arxiv_id":"2010.12083","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/language-conditioned-imitation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2010.12083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12083"}},"official":{"repos":["ir-lab/LanguagePolicies"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/robust-imitation-learning-from-noisy","slug":"robust-imitation-learning-from-noisy","title":"Robust Imitation Learning from Noisy Demonstrations","date":"2020-10-20","arxiv_id":"2010.10181","repositories_listed":1,"syntology":null},{"url":"/paper/training-stronger-baselines-for-learning-to","slug":"training-stronger-baselines-for-learning-to","title":"Training Stronger Baselines for Learning to Optimize","date":"2020-10-18","arxiv_id":"2010.09089","repositories_listed":1,"syntology":null},{"url":"/paper/self-imitation-learning-in-sparse-reward","slug":"self-imitation-learning-in-sparse-reward","title":"Self-Imitation Learning for Robot Tasks with Sparse and Delayed Rewards","date":"2020-10-14","arxiv_id":"2010.06962","repositories_listed":1,"syntology":null},{"url":"/paper/deep-imitation-learning-for-bimanual-robotic","slug":"deep-imitation-learning-for-bimanual-robotic","title":"Deep Imitation Learning for Bimanual Robotic Manipulation","date":"2020-10-11","arxiv_id":"2010.05134","repositories_listed":1,"syntology":null},{"url":"/paper/land-learning-to-navigate-from-disengagements","slug":"land-learning-to-navigate-from-disengagements","title":"LaND: Learning to Navigate from Disengagements","date":"2020-10-09","arxiv_id":"2010.04689","repositories_listed":1,"syntology":null},{"url":"/paper/provable-hierarchical-imitation-learning-via","slug":"provable-hierarchical-imitation-learning-via","title":"Provable Hierarchical Imitation Learning via EM","date":"2020-10-07","arxiv_id":"2010.03133","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generalize-for-sequential","slug":"learning-to-generalize-for-sequential","title":"Learning to Generalize for Sequential Decision Making","date":"2020-10-05","arxiv_id":"2010.02229","repositories_listed":1,"syntology":null},{"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/goal-auxiliary-actor-critic-for-6d-robotic","slug":"goal-auxiliary-actor-critic-for-6d-robotic","title":"Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds","date":"2020-10-02","arxiv_id":"2010.00824","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-reward-bias-in-adversarial","slug":"addressing-reward-bias-in-adversarial","title":"Addressing reward bias in Adversarial Imitation Learning with neutral reward functions","date":"2020-09-20","arxiv_id":"2009.09467","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-with-sinkhorn-distances","slug":"imitation-learning-with-sinkhorn-distances","title":"Imitation Learning with Sinkhorn Distances","date":"2020-08-20","arxiv_id":"2008.09167","repositories_listed":1,"syntology":null},{"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/interactive-imitation-learning-in-state-space","slug":"interactive-imitation-learning-in-state-space","title":"Interactive Imitation Learning in State-Space","date":"2020-08-02","arxiv_id":"2008.00524","repositories_listed":1,"syntology":null},{"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/learning-object-relation-graph-and-tentative","slug":"learning-object-relation-graph-and-tentative","title":"Learning Object Relation Graph and Tentative Policy for Visual Navigation","date":"2020-07-21","arxiv_id":"2007.11018","repositories_listed":1,"syntology":null},{"url":"/paper/iale-imitating-active-learner-ensembles","slug":"iale-imitating-active-learner-ensembles","title":"IALE: Imitating Active Learner Ensembles","date":"2020-07-09","arxiv_id":"2007.04637","repositories_listed":1,"syntology":null},{"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/scaling-imitation-learning-in-minecraft","slug":"scaling-imitation-learning-in-minecraft","title":"Scaling Imitation Learning in Minecraft","date":"2020-07-06","arxiv_id":"2007.02701","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-based-control-of","slug":"reinforcement-learning-based-control-of","title":"Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving","date":"2020-07-01","arxiv_id":"2007.00178","repositories_listed":1,"syntology":null},{"url":"/paper/an-imitation-learning-approach-for-cache","slug":"an-imitation-learning-approach-for-cache","title":"An Imitation Learning Approach for Cache Replacement","date":"2020-06-29","arxiv_id":"2006.16239","repositories_listed":1,"syntology":null},{"url":"/paper/lipschitzness-is-all-you-need-to-tame-off","slug":"lipschitzness-is-all-you-need-to-tame-off","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","date":"2020-06-28","arxiv_id":"2006.16785","repositories_listed":1,"syntology":null},{"url":"/paper/intrinsic-reward-driven-imitation-learning","slug":"intrinsic-reward-driven-imitation-learning","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","date":"2020-06-26","arxiv_id":"2006.15061","repositories_listed":1,"syntology":null},{"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/wasserstein-distance-guided-adversarial","slug":"wasserstein-distance-guided-adversarial","title":"Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration","date":"2020-06-05","arxiv_id":"2006.03503","repositories_listed":1,"syntology":null},{"url":"/paper/active-imitation-learning-with-noisy-guidance","slug":"active-imitation-learning-with-noisy-guidance","title":"Active Imitation Learning with Noisy Guidance","date":"2020-05-26","arxiv_id":"2005.12801","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-discovery-of-interpretable-planning","slug":"automatic-discovery-of-interpretable-planning","title":"Automatic Discovery of Interpretable Planning Strategies","date":"2020-05-24","arxiv_id":"2005.11730","repositories_listed":1,"syntology":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/off-policy-adversarial-inverse-reinforcement","slug":"off-policy-adversarial-inverse-reinforcement","title":"Off-Policy Adversarial Inverse Reinforcement Learning","date":"2020-05-03","arxiv_id":"2005.01138","repositories_listed":1,"syntology":null},{"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/vtgnet-a-vision-based-trajectory-generation","slug":"vtgnet-a-vision-based-trajectory-generation","title":"VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments","date":"2020-04-27","arxiv_id":"2004.12591","repositories_listed":1,"syntology":null},{"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/babyai-towards-grounded-language-learning","slug":"babyai-towards-grounded-language-learning","title":"Zero-Shot Compositional Policy Learning via Language Grounding","date":"2020-04-15","arxiv_id":"2004.07200","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-learning-for-fashion-style-based-on","slug":"imitation-learning-for-fashion-style-based-on","title":"Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation","date":"2020-04-13","arxiv_id":"2004.06229","repositories_listed":1,"syntology":null},{"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/augmented-q-imitation-learning-aqil","slug":"augmented-q-imitation-learning-aqil","title":"Augmented Q Imitation Learning (AQIL)","date":"2020-03-31","arxiv_id":"2004.00993","repositories_listed":1,"syntology":null},{"url":"/paper/goal-conditioned-end-to-end-visuomotor","slug":"goal-conditioned-end-to-end-visuomotor","title":"Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives","date":"2020-03-19","arxiv_id":"2003.08854","repositories_listed":1,"syntology":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/mqa-answering-the-question-via-robotic","slug":"mqa-answering-the-question-via-robotic","title":"MQA: Answering the Question via Robotic Manipulation","date":"2020-03-10","arxiv_id":"2003.04641","repositories_listed":1,"syntology":null},{"url":"/paper/mpc-guided-imitation-learning-of-neural","slug":"mpc-guided-imitation-learning-of-neural","title":"MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas","date":"2020-03-03","arxiv_id":"2003.01283","repositories_listed":1,"syntology":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/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/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/correlated-adversarial-imitation-learning","slug":"correlated-adversarial-imitation-learning","title":"Follow the Neurally-Perturbed Leader for Adversarial Training","date":"2020-02-16","arxiv_id":"2002.06476","repositories_listed":1,"syntology":null},{"url":"/paper/universal-value-density-estimation-for","slug":"universal-value-density-estimation-for","title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","date":"2020-02-15","arxiv_id":"2002.06473","repositories_listed":1,"syntology":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/discriminator-soft-actor-critic-without","slug":"discriminator-soft-actor-critic-without","title":"Discriminator Soft Actor Critic without Extrinsic Rewards","date":"2020-01-19","arxiv_id":"2001.06808","repositories_listed":1,"syntology":null},{"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/variational-imitation-learning-with-diverse","slug":"variational-imitation-learning-with-diverse","title":"Variational Imitation Learning with Diverse-quality Demonstrations","date":"2020-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/hierarchical-variational-imitation-learning","slug":"hierarchical-variational-imitation-learning","title":"Hierarchical Variational Imitation Learning of Control Programs","date":"2019-12-29","arxiv_id":"1912.12612","repositories_listed":1,"syntology":null},{"url":"/paper/compiler-auto-vectorization-with-imitation","slug":"compiler-auto-vectorization-with-imitation","title":"Compiler Auto-Vectorization with Imitation Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"d116af099e3946129d057abc592a4fbf9040483acf284ca0781abd7e18cd85c4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}