{"id":"W2921843114","doi":"10.65109/jvkr7103","title":"Reinforcement Learning in Stationary Mean-field Games","year":2019,"lang":"en","type":"article","venue":"","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Bounded rationality; Mean field theory; Bounded function; Field (mathematics); Class (philosophy); Computer science; Reinforcement; Mathematical optimization; Mathematics; Artificial intelligence; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001887029,0.00004228272,0.00007100164,0.00003831641,0.00008968345,0.00002090084,0.00006971162,0.00002657753,0.00192475],"category_scores_gemma":[0.00002146843,0.00004292611,0.00001906034,0.00005932428,0.0000280511,0.0001882157,0.00004435873,0.0000640068,0.0003657811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001362569,"about_ca_system_score_gemma":0.00003773755,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006677103,"about_ca_topic_score_gemma":0.003290388,"domain_scores_codex":[0.9995114,0.00002655269,0.0001157081,0.0001013809,0.00009851432,0.0001464056],"domain_scores_gemma":[0.9998181,0.00006835947,0.00002872501,0.0000468532,0.0000132233,0.00002472164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002222409,0.00004305913,0.7607011,0.000004785072,0.00000955707,0.000002228636,0.05625646,0.001745603,0.001518234,0.1731951,0.001714398,0.00478726],"study_design_scores_gemma":[0.002161259,0.0008396064,0.05589,0.00007847932,0.00001153131,5.4311e-7,0.7191416,0.001629014,0.01537804,0.003997276,0.1997977,0.001074956],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5645686,0.00004114064,0.00001329742,0.0006171786,0.00009230182,0.000118692,6.4702e-8,0.00002777829,0.434521],"genre_scores_gemma":[0.9697518,0.00007856473,0.0002196704,0.0002955907,0.00001620429,0.00001259241,0.000001539715,0.000003116841,0.02962088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7048111,"threshold_uncertainty_score":0.9999375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02734314869427392,"score_gpt":0.3325606142562802,"score_spread":0.3052174655620063,"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."}}