{"id":"W4405778703","doi":"10.1109/tits.2024.3515997","title":"Multiobjective Vehicle Routing Optimization With Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and NSGA-II","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Transportation Systems","topic":"Traffic control and management","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Info-communications Media Development Authority; National Natural Science Foundation of China; National Research Foundation Singapore","keywords":"Reinforcement learning; Vehicle routing problem; Computer science; Routing (electronic design automation); Multi-objective optimization; Mathematical optimization; Artificial intelligence; Machine learning; Computer network; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002094108,0.0002617658,0.0002340933,0.000274307,0.000252012,0.0001383056,0.00005532728,0.00006151419,0.000037822],"category_scores_gemma":[9.194709e-7,0.0002457243,0.0000776731,0.0002929359,0.00002822938,0.0002888201,3.423731e-7,0.0002569781,0.00001320446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001747119,"about_ca_system_score_gemma":0.00001900359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008716257,"about_ca_topic_score_gemma":0.00002042556,"domain_scores_codex":[0.9986443,0.00004510544,0.000439371,0.0003408939,0.0002787296,0.0002515937],"domain_scores_gemma":[0.9996399,0.00006084342,0.00004486502,0.0001072066,0.00006297016,0.00008419155],"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":[0.00004927522,0.00003617926,0.000005567046,0.0002749588,0.0002941638,0.000009741859,0.00296233,0.9886356,0.0005500332,0.00006131383,0.000003320341,0.00711749],"study_design_scores_gemma":[0.0003881436,0.0001303667,0.00001377457,0.0002998989,0.0002003828,0.00001348002,0.001342059,0.9956369,0.001386706,7.836476e-7,0.0003162731,0.0002712282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02047394,0.0003547126,0.9767431,0.000007314952,0.0004261346,0.000817079,0.00001177555,0.000789448,0.0003765058],"genre_scores_gemma":[0.9977491,0.0001127786,0.001390337,0.000005872818,0.00004760556,0.0001677188,0.00004203938,0.00006530511,0.0004192645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9772751,"threshold_uncertainty_score":0.9999995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009836098391936407,"score_gpt":0.2059355803819378,"score_spread":0.1960994819900014,"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."}}