{"id":"W2921997616","doi":"10.48550/arxiv.1903.03234","title":"Dyna-AIL : Adversarial Imitation Learning by Planning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Adversarial system; Imitation; Computer science; Convergence (economics); Differentiable function; Artificial intelligence; Machine learning; Control (management); State (computer science); Algorithm; Mathematics; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312763,0.0009025102,0.0009216584,0.0004408733,0.0003910176,0.0007461748,0.001857305,0.001158435,0.003391965],"category_scores_gemma":[0.003752831,0.0004744923,0.0005198331,0.0003861407,0.001468831,0.0011954,0.002094118,0.002180566,0.0007604934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007113771,"about_ca_system_score_gemma":0.001099309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002659917,"about_ca_topic_score_gemma":0.002365246,"domain_scores_codex":[0.9994247,0.0002133749,0.00002723061,0.0001238711,0.0001608155,0.00004994719],"domain_scores_gemma":[0.9984187,0.001047945,0.0001368834,0.0002059998,0.0001159995,0.00007442854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005209644,0.00003307629,0.0002523034,0.00006047911,0.00003888218,0.00006269251,0.00003756702,0.9342958,0.001546891,0.02579883,0.001441518,0.03637973],"study_design_scores_gemma":[0.000003471528,0.00001117974,0.00001680016,0.000002641478,0.000001774235,0.00000848514,0.000001491441,0.9936455,0.0003544939,0.005535414,0.0004159512,0.00000277489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004031329,0.0001289857,0.9927816,0.0001358002,0.00003420467,0.0000348799,0.00003540627,0.0009632049,0.001854652],"genre_scores_gemma":[0.662885,0.0003068214,0.3279972,0.0003104013,0.00006313527,0.0003357446,0.0002440782,0.0004667646,0.00739093],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003391965,"threshold_uncertainty_score":0.01134723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04934010721025346,"score_gpt":0.2025524040767681,"score_spread":0.1532122968665147,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}