{"id":"W7126372933","doi":"10.21428/594757db.52f0016b","title":"Edge-DIRECT: A Deep Reinforcement Learning-based Method for Solving Heterogeneous Electric Vehicle Routing Problem with Time Window Constraints","year":2024,"lang":"en","type":"article","venue":"","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Vehicle routing problem; Focus (optics); Electric vehicle; Routing (electronic design automation); Reinforcement learning; Key (lock)","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":[0.001224278,0.0003358706,0.0003488513,0.0002577534,0.000194176,0.0002473991,0.0001613505,0.0001342088,0.0002951414],"category_scores_gemma":[0.0001536103,0.0003092393,0.0001273627,0.0006830681,0.00003212035,0.0001464322,0.00002749665,0.0003317925,0.00004930077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002391527,"about_ca_system_score_gemma":0.0001189015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000888201,"about_ca_topic_score_gemma":0.000004026854,"domain_scores_codex":[0.9980485,0.0001101995,0.0004549744,0.0004501234,0.0002566302,0.0006795587],"domain_scores_gemma":[0.9986725,0.0007926231,0.00006254025,0.0002145745,0.0001220526,0.0001357523],"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":[0.00002060143,0.000009598059,0.00004677477,0.0002292246,0.0001468775,0.00001192352,0.000222752,0.9445105,0.0204219,0.0001111407,0.00006047791,0.03420822],"study_design_scores_gemma":[0.0005825919,0.0002041914,0.000004967399,0.000160392,0.00008113332,0.0000349648,0.00002147332,0.9308944,0.06716356,0.00002127758,0.0004421747,0.0003888957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001513299,0.0002477112,0.9868736,0.00006334252,0.00009392446,0.0008244853,0.000001561265,0.002583242,0.007798845],"genre_scores_gemma":[0.5688353,0.000003693756,0.4300193,0.00006387694,0.00007328483,0.0001238153,0.00001796201,0.0001320133,0.000730813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.567322,"threshold_uncertainty_score":0.999936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00910362427285603,"score_gpt":0.2495874737083705,"score_spread":0.2404838494355145,"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."}}