{"id":"W4401072134","doi":"10.1016/j.trb.2024.103027","title":"Approximate dynamic programming for pickup and delivery problem with crowd-shipping","year":2024,"lang":"en","type":"article","venue":"Transportation Research Part B Methodological","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Markov decision process; Dynamic programming; Mathematical optimization; Matching (statistics); Scalability; Bellman equation; Convergence (economics); Stochastic programming; Pickup; Markov process; Function (biology); Operations research; Engineering; Mathematics; Algorithm; Artificial intelligence","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":[0.002284693,0.0001640126,0.0002139932,0.0002397715,0.0001782377,0.0001273667,0.00009332482,0.0001287064,0.00004785257],"category_scores_gemma":[0.00004997213,0.0001312838,0.00005703012,0.0006777698,0.0002073919,0.000221019,0.000002190448,0.0004280508,0.000004538376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004180477,"about_ca_system_score_gemma":0.00005732765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001489402,"about_ca_topic_score_gemma":0.0002764448,"domain_scores_codex":[0.9983481,0.0001366542,0.0003732061,0.0003860325,0.0003088477,0.0004472298],"domain_scores_gemma":[0.9984943,0.001034018,0.00001595993,0.0001297137,0.0002115019,0.000114555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001121125,0.0004452452,0.01351919,0.0156317,0.001140219,0.0002874036,0.01454095,0.05261488,0.05457736,0.2861295,0.002185532,0.5578069],"study_design_scores_gemma":[0.005398917,0.003012271,0.326783,0.002370206,0.0006082111,0.00005402188,0.007744208,0.2240861,0.01240318,0.04221868,0.3722356,0.003085625],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4364312,0.000523783,0.5600631,0.0004531909,0.00008730036,0.001368744,0.00009093022,0.0008122451,0.0001695102],"genre_scores_gemma":[0.7339423,0.0001445759,0.2641114,0.00002156947,0.00003643378,0.001237884,0.000322497,0.00003952491,0.0001438447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5547213,"threshold_uncertainty_score":0.5353596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2657432137070771,"score_gpt":0.4298331329529043,"score_spread":0.1640899192458272,"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."}}