{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006385845,0.0001886214,0.0002026095,0.0001211017,0.0001814106,0.00002570637,0.0001176452,0.00005932527,0.00002222441],"category_scores_gemma":[0.0000125218,0.0001471677,0.0000254295,0.0004742122,0.00005630156,0.00005785724,0.0000326101,0.0005229475,0.000001898202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004546199,"about_ca_system_score_gemma":0.00002507831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009728158,"about_ca_topic_score_gemma":0.00008801147,"domain_scores_codex":[0.9992016,0.00001854544,0.0002181674,0.0002128688,0.0001293568,0.0002194766],"domain_scores_gemma":[0.9995596,0.00004183251,0.0000858855,0.000184375,0.00005787481,0.00007047381],"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":[0.00001953926,0.00002333686,0.07334997,0.0001074,0.00008693511,8.019808e-7,0.000204521,0.901118,0.001193041,0.0002994162,0.00001407411,0.02358297],"study_design_scores_gemma":[0.0008224685,0.0001964024,0.03303423,0.0000892849,0.00007260309,0.000009691966,0.0002031604,0.952168,0.0009461604,0.00001007736,0.01223761,0.000210229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3024382,0.0008506055,0.6955246,0.000119959,0.000009809105,0.0003852475,0.000003264166,0.0002269132,0.0004414414],"genre_scores_gemma":[0.9708681,0.0001494394,0.02814393,0.00002677409,0.00002002611,0.0001107489,0.00009290998,0.00003272403,0.0005553885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6684299,"threshold_uncertainty_score":0.6001326,"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."}}