{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008200503,0.0005146084,0.0005158625,0.0003603432,0.0003757121,0.0002548003,0.002425145,0.00056889,0.00003959542],"category_scores_gemma":[0.0002971616,0.0006572715,0.0002749505,0.0006041662,0.00009386776,0.0008868128,0.00321126,0.002227685,0.0002054258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005152412,"about_ca_system_score_gemma":0.0002777997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001897064,"about_ca_topic_score_gemma":0.000007541199,"domain_scores_codex":[0.9966605,0.0004232655,0.0003522242,0.001671494,0.0002403733,0.0006521456],"domain_scores_gemma":[0.9972834,0.0005188942,0.0007011033,0.001121956,0.0001760863,0.000198576],"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":[0.00005997014,0.00003129698,0.00801353,0.00006415789,0.0000966759,0.0001760743,0.0007953685,0.9702039,0.00006665957,0.01868998,0.0006435543,0.001158778],"study_design_scores_gemma":[0.0009708505,0.00008191962,0.001100971,0.0001594231,0.00008416767,0.000004370356,0.0003630367,0.988008,0.00004529277,0.005672525,0.002730956,0.000778524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06916577,0.00009474959,0.9210115,0.0001065379,0.002385753,0.0003309944,0.000006213545,0.0006099382,0.006288549],"genre_scores_gemma":[0.9904023,0.00003229237,0.005195112,0.0000633981,0.0002730035,7.985292e-7,0.0001025527,0.00004954923,0.00388093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9212366,"threshold_uncertainty_score":0.9995878,"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."}}