{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003703042,0.001567283,0.002743991,0.0008750753,0.0006169169,0.001424605,0.002285714,0.002863267,0.002980146],"category_scores_gemma":[0.01046085,0.001018185,0.0008173886,0.0006870895,0.00192813,0.001591756,0.002186373,0.00299843,0.0004602548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002228358,"about_ca_system_score_gemma":0.002492156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01058067,"about_ca_topic_score_gemma":0.008884819,"domain_scores_codex":[0.9989807,0.000504341,0.000048421,0.0001789247,0.0001407252,0.0001468354],"domain_scores_gemma":[0.9916909,0.006994278,0.0003530848,0.0001388232,0.0004710429,0.0003517643],"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":[0.00007049329,0.00004303817,0.0002930156,0.00003744831,0.00003721192,0.00002557716,0.00003517601,0.9797794,0.0001399658,0.01144894,0.0005659892,0.007523715],"study_design_scores_gemma":[0.00001363793,0.00001105108,0.00001766666,0.000003855268,0.000003146443,0.000002339405,0.00000274384,0.9959211,0.00002644299,0.003932895,0.00006274573,0.000002282921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02328075,0.0005057761,0.9711311,0.0005816076,0.0001029657,0.00007651839,0.00005177162,0.0002301348,0.004039341],"genre_scores_gemma":[0.8505577,0.0004413985,0.1393136,0.000380991,0.0001283765,0.000420298,0.0002013622,0.0001593701,0.008396888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01058067,"threshold_uncertainty_score":0.02103817,"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."}}