{"id":"W4409753650","doi":"10.1016/j.eswa.2025.127818","title":"Reinforcement learning-based algorithm for the dynamic multi-depot crowdsourced delivery problem","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Manufacturing and Logistics Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Depot; Artificial intelligence; Machine learning; Algorithm; Mathematical optimization; 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":[0.001614754,0.001098468,0.002457693,0.0007350294,0.0008078723,0.001032991,0.002967557,0.00234109,0.005099315],"category_scores_gemma":[0.003503413,0.0007096065,0.0007535029,0.00080235,0.001190383,0.00111904,0.002131224,0.001966157,0.0006517327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001754158,"about_ca_system_score_gemma":0.003221336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01633516,"about_ca_topic_score_gemma":0.01104491,"domain_scores_codex":[0.9994017,0.0001545722,0.000023444,0.0001452949,0.0001262534,0.0001486726],"domain_scores_gemma":[0.9979481,0.00137413,0.000156894,0.00007193133,0.0002693124,0.0001795976],"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":[0.00009200849,0.00006518397,0.0002592951,0.0000451622,0.00002385095,0.00003758051,0.00002611331,0.9750137,0.0002840141,0.003009716,0.001180988,0.01996239],"study_design_scores_gemma":[0.00002229469,0.0000146997,0.00002743128,0.00000342661,0.00000315282,0.000004844218,0.000003797533,0.9986386,0.00005622287,0.001094106,0.000128826,0.000002501874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02760812,0.0004014032,0.9651675,0.0006123928,0.0001456896,0.0001565194,0.0001093806,0.00052748,0.005271529],"genre_scores_gemma":[0.8019705,0.0002467787,0.1883299,0.0004071551,0.0001158812,0.0003735751,0.000288783,0.0001339487,0.008133451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01633516,"threshold_uncertainty_score":0.03248018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00787518912783338,"score_gpt":0.2394139049717775,"score_spread":0.2315387158439441,"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."}}