{"id":"W4377091056","doi":"10.1016/j.jedc.2023.104670","title":"A Gradient-based reinforcement learning model of market equilibration","year":2023,"lang":"en","type":"article","venue":"Journal of Economic Dynamics and Control","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Brock University","funders":"","keywords":"Reinforcement learning; Stochastic game; Fictitious play; Stability (learning theory); Computer science; Mathematical optimization; Reinforcement; Mathematical economics; Economics; Game theory; Mathematics; Artificial intelligence; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0007457419,0.00006778051,0.0002338787,0.0001231117,0.0001371308,0.00003997869,0.0001001022,0.00003832172,0.00002761204],"category_scores_gemma":[0.00003082343,0.00006901068,0.00009173576,0.00003468699,0.000103562,0.000210951,0.00002318112,0.00007859803,0.000002518045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002576836,"about_ca_system_score_gemma":0.000149484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000123588,"about_ca_topic_score_gemma":0.0003305679,"domain_scores_codex":[0.9992477,0.00004101887,0.0004172514,0.00007617713,0.00006873978,0.0001491398],"domain_scores_gemma":[0.9993069,0.00008579629,0.0004514104,0.00004734279,0.00004081552,0.00006770113],"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":[0.0003864009,0.00005527967,0.04633237,0.00002227231,0.0001743756,0.000004125678,0.003690921,0.8481191,0.002463049,0.09343073,0.0005038347,0.004817537],"study_design_scores_gemma":[0.0009811092,0.0001356751,0.00039243,0.00001391398,0.0000255229,4.113117e-7,0.002076076,0.9946862,0.00003752497,0.001507411,0.00007564835,0.00006809689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886652,0.00008165091,0.003073146,0.001103459,0.0002452159,0.0001342526,0.000009844811,0.00001108155,0.006676158],"genre_scores_gemma":[0.9987474,0.0002158686,0.000137396,0.00004262214,0.00005845791,0.000003957541,0.000002034901,0.000006861849,0.0007854167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1465671,"threshold_uncertainty_score":0.2814174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01979059109830348,"score_gpt":0.2846521386873085,"score_spread":0.264861547589005,"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."}}