{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002186898,0.0006175987,0.001048059,0.0004007539,0.0004783789,0.0009019412,0.0009632664,0.00120598,0.00154353],"category_scores_gemma":[0.006719943,0.0002964146,0.0005759282,0.000323307,0.001848731,0.001179066,0.0009002472,0.001201424,0.0001487758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001481229,"about_ca_system_score_gemma":0.001078717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004748511,"about_ca_topic_score_gemma":0.002370046,"domain_scores_codex":[0.9992274,0.0004539281,0.00002676156,0.0001030864,0.0001027603,0.00008595904],"domain_scores_gemma":[0.9965069,0.002790636,0.0002745498,0.00008337535,0.0001958163,0.000148764],"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":[0.000052812,0.00004674682,0.000628225,0.00005414897,0.00002727738,0.0000691212,0.00007742189,0.8968337,0.000721716,0.09302423,0.0004281743,0.00803642],"study_design_scores_gemma":[0.00001800989,0.00002138827,0.00007469597,0.000004489574,0.00000361116,0.000007088727,0.00001004923,0.9654136,0.0001218445,0.03412587,0.0001946998,0.0000045678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1113468,0.0003753524,0.8816016,0.0008399642,0.0000493773,0.00006991608,0.00003681165,0.0001204763,0.005559671],"genre_scores_gemma":[0.961397,0.0002221454,0.03587946,0.0001083612,0.00002564186,0.0001086108,0.00003024503,0.00001701974,0.002211459],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004748511,"threshold_uncertainty_score":0.01156557,"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."}}