{"id":"W4391022010","doi":"10.1109/cdc49753.2023.10383868","title":"Learning Optimal Policies in Mean Field Models with Kullback-Leibler Regularization","year":2023,"lang":"en","type":"article","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Emera (Canada)","funders":"Agence Nationale de la Recherche; National Science Foundation","keywords":"Regularization (linguistics); Kullback–Leibler divergence; Computer science; Field (mathematics); Artificial intelligence; Machine learning; 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":[0.00392773,0.001051942,0.002030472,0.0008230563,0.0004939159,0.00174547,0.001395149,0.002078142,0.001524535],"category_scores_gemma":[0.01171162,0.0007777372,0.000771452,0.0007174409,0.002588928,0.002606893,0.001618206,0.002058044,0.0002618171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002139542,"about_ca_system_score_gemma":0.002472956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00747708,"about_ca_topic_score_gemma":0.005994241,"domain_scores_codex":[0.9985953,0.0007536314,0.00005552413,0.0002344105,0.0002264001,0.0001347018],"domain_scores_gemma":[0.9941817,0.00474966,0.0004322052,0.0001617574,0.0003030251,0.0001716405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003945588,0.00003873117,0.0003429031,0.00006171641,0.00003366634,0.00003723408,0.00005004247,0.9049649,0.0002438504,0.08504578,0.0007056656,0.00843614],"study_design_scores_gemma":[0.000006296847,0.00001221766,0.00003685696,0.00000512483,0.000002427276,0.000004407426,0.000003663277,0.9645863,0.00004861984,0.03516357,0.0001252031,0.000005224349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01598664,0.0003882156,0.9809137,0.0006219177,0.00003204154,0.00002640531,0.00004206547,0.0001590762,0.00182987],"genre_scores_gemma":[0.8639643,0.0008590187,0.1274443,0.0004159088,0.0001503142,0.0002980405,0.0001638566,0.0001281294,0.006576076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00747708,"threshold_uncertainty_score":0.0207721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01158774867596724,"score_gpt":0.1968304539561419,"score_spread":0.1852427052801747,"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."}}