{"id":"W4404636053","doi":"10.1016/j.cie.2024.110711","title":"MERCI: Multi-agent reinforcement learning for enhancing on-demand Electric taxi operation in terms of Rebalancing, Charging, and Informing Orders","year":2024,"lang":"en","type":"article","venue":"Computers & Industrial Engineering","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China; Canada Foundation for Innovation","keywords":"Reinforcement learning; Reinforcement; On demand; Automotive engineering; Computer science; Engineering; Business; Artificial intelligence; Structural engineering; Multimedia","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002851596,0.0001731112,0.0002090347,0.0004816656,0.0000433277,0.00005668409,0.00006533677,0.0001097582,0.000004460183],"category_scores_gemma":[0.00006012941,0.0001917471,0.00004493784,0.0004001621,0.000007940236,0.0001988077,0.00000981934,0.0003317575,0.000001120367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001368138,"about_ca_system_score_gemma":0.00002723916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001794045,"about_ca_topic_score_gemma":0.00001624682,"domain_scores_codex":[0.9989772,0.000006146977,0.0004934177,0.0001748272,0.0001109104,0.0002374564],"domain_scores_gemma":[0.9997044,0.0001089701,0.00003310483,0.0000855977,0.00002039433,0.00004750805],"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":[0.000006713605,0.000006383258,0.0001996716,0.000203928,0.00004065992,0.000001909422,0.0009397087,0.9703531,0.01791027,0.001051316,0.00003495524,0.009251428],"study_design_scores_gemma":[0.0008761226,0.00008207827,0.0005724216,0.0004810361,0.00001506681,0.000001905488,0.00004101928,0.9817266,0.01301305,0.000002486105,0.003000866,0.000187342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3422073,0.0001059728,0.6559349,0.00003268923,0.0008714566,0.0005349876,0.000002396361,0.0002690504,0.00004124203],"genre_scores_gemma":[0.9982043,0.00004072876,0.001471355,0.00001454818,0.0001143912,0.00006227547,0.00004228672,0.00003065724,0.00001949387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.655997,"threshold_uncertainty_score":0.7819219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01918843082513213,"score_gpt":0.2339128933114853,"score_spread":0.2147244624863532,"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."}}