{"id":"W4406213014","doi":"10.1016/j.mlwa.2025.100620","title":"Multi-agent deep reinforcement learning with online and fair optimal dispatch of EV aggregators","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Electric Vehicles and Infrastructure","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; 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":[0.001088322,0.000831302,0.0009575037,0.0002162356,0.0003465112,0.0006720601,0.001229392,0.000797838,0.001389693],"category_scores_gemma":[0.002492213,0.0004143489,0.0003637608,0.0002022858,0.0007121371,0.0006781139,0.0009468438,0.001255069,0.0002036478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008992048,"about_ca_system_score_gemma":0.001431433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01099617,"about_ca_topic_score_gemma":0.008980466,"domain_scores_codex":[0.9996455,0.00009413178,0.00001745871,0.00008206163,0.00006798926,0.00009278914],"domain_scores_gemma":[0.9991517,0.00039744,0.000108012,0.00006261642,0.0001998264,0.00008035822],"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":[0.00006349271,0.00005229906,0.0005856921,0.00001999324,0.00001650658,0.00004618678,0.00002349466,0.9815394,0.0005662215,0.001700984,0.0004108207,0.01497492],"study_design_scores_gemma":[0.000003100732,0.000007807439,0.00002374455,6.788408e-7,0.000001201936,0.000001518663,0.000001385722,0.9995479,0.00006176851,0.0003178932,0.00003228083,7.215577e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1262569,0.0004261016,0.8671688,0.0005123744,0.0001169835,0.00007516423,0.00005943509,0.0009115987,0.00447254],"genre_scores_gemma":[0.9761993,0.00005228586,0.02201756,0.0001048142,0.00001935114,0.00004741435,0.00004280711,0.00001969832,0.001496822],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01099617,"threshold_uncertainty_score":0.0218643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003117776452914673,"score_gpt":0.2086875150646737,"score_spread":0.205569738611759,"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."}}