{"id":"W4404612065","doi":"10.1145/3678717.3691208","title":"EFECTIW-ROTER: Deep Reinforcement Learning Approach for Solving Heterogeneous Fleet and Demand Vehicle Routing Problem With Time-Window Constraints","year":2024,"lang":"en","type":"article","venue":"","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Calgary","funders":"","keywords":"Reinforcement learning; Vehicle routing problem; Computer science; Window (computing); Routing (electronic design automation); Artificial intelligence; Operations research; Real-time computing; Computer network; Engineering; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008457622,0.0002574741,0.0002511715,0.0001135208,0.0002197336,0.0002970794,0.00008497886,0.0001053723,0.00006413918],"category_scores_gemma":[0.00005478102,0.0002290854,0.00005592054,0.0001929254,0.00006256405,0.0001952084,0.00005178816,0.0002887866,0.000008852315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008308105,"about_ca_system_score_gemma":0.0000230341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004269903,"about_ca_topic_score_gemma":0.000001508704,"domain_scores_codex":[0.9986553,0.00004669619,0.0003188207,0.0003714129,0.0001619528,0.0004457818],"domain_scores_gemma":[0.9994091,0.0002544441,0.0000385305,0.0001376084,0.00004965581,0.0001106768],"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":[0.00001138129,0.000005665422,0.0004798865,0.0004017554,0.0001371453,0.000005455749,0.0006917473,0.9778355,0.004699163,0.0001734977,0.00001543269,0.01554331],"study_design_scores_gemma":[0.0005245324,0.0001179262,0.00002145377,0.0001297452,0.00005463132,0.00009884133,0.0001133992,0.9913825,0.007134543,0.00001918618,0.00009729993,0.000305972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04367941,0.0002852533,0.9471446,0.00001759631,0.00004644859,0.0007321255,0.000001142569,0.001057213,0.007036211],"genre_scores_gemma":[0.7145485,0.00001152155,0.2848569,0.0000199697,0.00005438186,0.00005980287,0.00001654112,0.00007736457,0.0003550468],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6708691,"threshold_uncertainty_score":0.9341831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01007328597245367,"score_gpt":0.2279551237146681,"score_spread":0.2178818377422145,"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."}}