{"id":"W4398144166","doi":"10.1007/s00245-024-10138-1","title":"Actor-Critic Reinforcement Learning Algorithms for Mean Field Games in Continuous Time, State and Action Spaces","year":2024,"lang":"en","type":"article","venue":"Applied Mathematics & Optimization","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Action (physics); Field (mathematics); State (computer science); Reinforcement; Computer science; Mathematics; Artificial intelligence; Algorithm; Psychology; Social psychology; Physics; Pure mathematics","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":[0.0002335589,0.00011734,0.0002323576,0.0001600904,0.00007998537,0.0001531539,0.00006198604,0.00006873727,0.0000449406],"category_scores_gemma":[0.0000810963,0.000133724,0.00002980792,0.0001868369,0.00001993221,0.0001268074,0.00002584953,0.00009497008,0.00005026468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004731974,"about_ca_system_score_gemma":0.0000139877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002275489,"about_ca_topic_score_gemma":0.000005286157,"domain_scores_codex":[0.9991382,9.918259e-7,0.0004023199,0.0002577913,0.0000326976,0.0001680443],"domain_scores_gemma":[0.9995249,0.0001824682,0.0001353114,0.00009932015,0.00002634333,0.00003166121],"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":[0.00001352587,0.00005376742,0.00001379578,0.0004887896,0.00002887087,4.902779e-7,0.002124891,0.07543515,0.0001309165,0.9094918,0.00009603201,0.01212196],"study_design_scores_gemma":[0.0002404767,0.00005428021,0.00001029948,0.00005466296,0.00001160889,0.000001479125,0.0002435406,0.81392,0.0002331864,0.1838573,0.001212763,0.000160348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001543764,0.0003820815,0.9934203,0.0002173754,0.00006710601,0.0005651299,0.00001325968,0.00005911207,0.003731859],"genre_scores_gemma":[0.7347196,0.0006261521,0.2621266,0.0001129018,0.0001206542,0.00080173,0.0001018446,0.00006747724,0.001323019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7384849,"threshold_uncertainty_score":0.5453107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02115378242548192,"score_gpt":0.2475767698477827,"score_spread":0.2264229874223008,"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."}}