{"id":"W3199472824","doi":"","title":"Off-line approximate dynamic programming for the vehicle routing problem with stochastic customers and demands via decentralized decision-making","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Transportation and Mobility Innovations","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Markov decision process; Computer science; Mathematical optimization; Vehicle routing problem; Reinforcement learning; Heuristic; Benchmark (surveying); Dynamic programming; Set (abstract data type); Routing (electronic design automation); Dimension (graph theory); Stochastic programming; Operations research; Markov process; Artificial intelligence; Mathematics; Algorithm","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":[0.002097341,0.0014543,0.001958217,0.0005700554,0.000559251,0.001378536,0.001331442,0.001687302,0.002864127],"category_scores_gemma":[0.005518881,0.0008031658,0.000836329,0.0008404804,0.001277025,0.001232446,0.001378193,0.001944393,0.0003380207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001700054,"about_ca_system_score_gemma":0.002665179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008157298,"about_ca_topic_score_gemma":0.007267231,"domain_scores_codex":[0.9987722,0.0005554351,0.0000363771,0.0002236739,0.000225223,0.0001869593],"domain_scores_gemma":[0.9963114,0.002873311,0.0003367454,0.000094902,0.0002386184,0.0001450989],"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":[0.00002415543,0.00002489829,0.0001385462,0.0000251586,0.00001086881,0.00002533909,0.00001507383,0.9911192,0.00008465719,0.004772092,0.0002097845,0.00355019],"study_design_scores_gemma":[0.000006227532,0.000008647498,0.00001954346,0.000002345527,0.000001674825,0.000002903948,0.000003379512,0.9970432,0.00002661103,0.002786521,0.00009768293,0.000001265356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02730552,0.0004463614,0.9667635,0.0005600439,0.00005324462,0.0001138567,0.0000995101,0.0001858147,0.004472128],"genre_scores_gemma":[0.8601236,0.0004702776,0.1341198,0.0002317983,0.00008380924,0.0004274603,0.0002566554,0.00009284572,0.004193762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008157298,"threshold_uncertainty_score":0.01621968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02276891013377397,"score_gpt":0.2002714649641362,"score_spread":0.1775025548303622,"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."}}