{"id":"W3102502161","doi":"","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","year":2020,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; McGill University; Université de Montréal","funders":"","keywords":"Discriminator; Adversarial system; Reinforcement learning; Computer science; Generator (circuit theory); Imitation; Artificial intelligence; Machine learning; Optimization problem; Mathematical optimization; Algorithm; Power (physics); Mathematics","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":[0.002595028,0.001247263,0.001353115,0.0005886242,0.0004474133,0.001123688,0.002436131,0.001922339,0.005033266],"category_scores_gemma":[0.01050621,0.0005635112,0.0006548373,0.0005021137,0.002216509,0.002280615,0.003523013,0.003021135,0.001217628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009835806,"about_ca_system_score_gemma":0.001338227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001705303,"about_ca_topic_score_gemma":0.001808532,"domain_scores_codex":[0.9988639,0.0003745827,0.00005556885,0.0002426425,0.0003423567,0.0001208956],"domain_scores_gemma":[0.9960144,0.0026363,0.0002938643,0.0006478663,0.000228105,0.0001795065],"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":[0.0001201549,0.00007325972,0.0006151577,0.00008113242,0.00004972933,0.0001301966,0.00007135916,0.8901227,0.002476091,0.04543509,0.001951403,0.05887379],"study_design_scores_gemma":[0.000007690638,0.00001892199,0.00003474327,0.000006325814,0.00000334289,0.00001886917,0.000003258956,0.9864044,0.0006219011,0.01248364,0.0003918574,0.000005093517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01016759,0.0001711025,0.9843343,0.0003276392,0.00004658995,0.0000598861,0.0000417078,0.0008857191,0.003965546],"genre_scores_gemma":[0.7687337,0.0002186097,0.2201864,0.000564162,0.00009327436,0.000271738,0.0001878865,0.0004540351,0.009290138],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005033266,"threshold_uncertainty_score":0.01683789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01128101256007434,"score_gpt":0.250604166278861,"score_spread":0.2393231537187866,"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."}}