{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007845568,0.001412661,0.001254037,0.00117871,0.001418331,0.002778889,0.003609876,0.003398844,0.007167538],"category_scores_gemma":[0.03889206,0.0008166754,0.001115879,0.0009724054,0.005019299,0.006005349,0.004271799,0.009424887,0.001581983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002361172,"about_ca_system_score_gemma":0.001996958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009350926,"about_ca_topic_score_gemma":0.0007723078,"domain_scores_codex":[0.9941094,0.002520796,0.0002924091,0.0007481475,0.001950598,0.0003787354],"domain_scores_gemma":[0.9781232,0.01560126,0.0009662672,0.002286039,0.002476113,0.0005469749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003946964,0.0000241329,0.000127705,0.0000568763,0.00001344308,0.0000432273,0.00006153607,0.04436367,0.0003958807,0.9452723,0.001185057,0.008416714],"study_design_scores_gemma":[0.00003126157,0.00001964213,0.00003367229,0.00003116614,0.000006676081,0.00003344162,0.00001390847,0.3231652,0.0005301476,0.6740592,0.002065311,0.00001038699],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00541495,0.0003555672,0.9769357,0.002377437,0.0001375893,0.00004440521,0.00005516449,0.0002019926,0.01447719],"genre_scores_gemma":[0.6582749,0.001180762,0.3271579,0.001752665,0.000697031,0.0006360652,0.0002775294,0.0005874484,0.009435819],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007845568,"threshold_uncertainty_score":0.04149181,"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."}}