{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007464612,0.0001500212,0.0001273866,0.00006768872,0.0003459509,0.00005526993,0.0001526391,0.00005799826,0.000002111714],"category_scores_gemma":[0.000006500781,0.0001097842,0.00003485584,0.0001564044,0.0000376457,0.00003790468,0.00001250853,0.000110146,0.000005929018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001257905,"about_ca_system_score_gemma":0.00002958891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004823668,"about_ca_topic_score_gemma":0.00001132705,"domain_scores_codex":[0.9993111,0.00001103932,0.0002188556,0.0001825821,0.00008838696,0.0001880387],"domain_scores_gemma":[0.999357,0.0001618,0.00005607653,0.0002966329,0.00009424489,0.0000341862],"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":[0.000004338729,0.00001326978,0.000002144952,0.00007032041,0.00004464522,1.239917e-7,0.00007760195,0.9871669,0.00007570034,0.0003681153,0.0002705307,0.01190632],"study_design_scores_gemma":[0.0004741128,0.00001923181,0.000008226119,0.00004822085,0.00001964031,0.000001006978,0.000202933,0.9258768,0.0004627449,0.00001153484,0.07274837,0.000127158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000006331462,0.001494643,0.9955608,0.00007691225,0.00008894771,0.001933154,0.000007584701,0.0004802329,0.0003513496],"genre_scores_gemma":[0.6896827,0.0001834069,0.2877997,0.00009112938,0.00008615098,0.01797577,0.0001952659,0.00007200822,0.003913886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7077612,"threshold_uncertainty_score":0.447687,"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."}}