{"id":"W4407091303","doi":"10.48550/arxiv.2501.19116","title":"A Theoretical Justification for Asymmetric Actor-Critic Algorithms","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Group for Research in Decision Analysis; HEC Montréal","funders":"Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture","keywords":"Algorithm; Computer science; Mathematical economics; Economics","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":[0.001339877,0.0006272451,0.0007798703,0.0006592641,0.0002638916,0.0004213866,0.003744696,0.0006374173,0.00004435676],"category_scores_gemma":[0.001828533,0.0006195148,0.0005155093,0.001308645,0.0003506394,0.000252151,0.00368497,0.001024913,0.000106346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004287408,"about_ca_system_score_gemma":0.0006518628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004288653,"about_ca_topic_score_gemma":0.000003834915,"domain_scores_codex":[0.9951993,0.0003092588,0.0008836508,0.002172799,0.0006092293,0.0008257147],"domain_scores_gemma":[0.9938404,0.001945103,0.0002790391,0.002910673,0.0007651713,0.0002596222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002694359,0.0008463612,0.008940126,0.001125698,0.0001992956,0.00002187971,0.0006943344,0.0006168248,0.00009499624,0.6913437,0.001420932,0.2946689],"study_design_scores_gemma":[0.0007906411,0.0002281765,0.05330735,0.0002348131,0.0001980894,0.00001632252,0.00004163429,0.6282699,0.001805733,0.3103986,0.003444995,0.001263772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01870117,0.0006137415,0.9663768,0.004052841,0.005333079,0.001789938,0.00009942069,0.0007912767,0.002241694],"genre_scores_gemma":[0.8329238,0.00005779498,0.1645372,0.000556726,0.0007704224,0.0006174707,0.00009422257,0.00003583448,0.0004064857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8142226,"threshold_uncertainty_score":0.9996256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05607602837467341,"score_gpt":0.3211562526190507,"score_spread":0.2650802242443773,"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."}}