{"id":"W4413979703","doi":"10.1109/tits.2025.3601536","title":"Real-Time Matching and Dispatching for Urban Freight Transportation: A Hierarchical Reinforcement Learning Through Actor-Critic and H3 Spatial Partitioning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Urban and Freight Transport Logistics","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Matching (statistics); Computer science; Transport engineering; Travel time; Artificial intelligence; Operations research; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.000919128,0.0006599146,0.000736564,0.0002851988,0.0003804865,0.0006636666,0.001337649,0.000863046,0.002002732],"category_scores_gemma":[0.002015283,0.0004301413,0.000430778,0.0002761511,0.000922686,0.0008988048,0.001055644,0.001139607,0.0003041154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001138584,"about_ca_system_score_gemma":0.001337221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01421531,"about_ca_topic_score_gemma":0.01111447,"domain_scores_codex":[0.999647,0.0001055308,0.00001230903,0.0001064814,0.00005639936,0.00007229987],"domain_scores_gemma":[0.999332,0.0003445313,0.00009129616,0.00004993846,0.000102587,0.00007963175],"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":[0.0000450627,0.00003370158,0.0006481471,0.00001423929,0.00001962783,0.00003551817,0.00002977264,0.98299,0.0007323037,0.002910508,0.0004684837,0.01207262],"study_design_scores_gemma":[0.000002899651,0.000005545749,0.00003408919,7.855283e-7,0.000001619936,0.000001940715,0.000001911308,0.9992662,0.00006955885,0.0005557885,0.0000584433,0.000001071289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05781461,0.0001611505,0.9377533,0.0003748016,0.00003829796,0.00004587728,0.00004846614,0.0005246433,0.003238788],"genre_scores_gemma":[0.9518011,0.00005834255,0.04548184,0.0001536112,0.00001945892,0.0000644076,0.00007081891,0.00005068841,0.002299947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01421531,"threshold_uncertainty_score":0.02826518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01690899965056009,"score_gpt":0.2360636984879829,"score_spread":0.2191546988374228,"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."}}