{"id":"W7117476694","doi":"10.1016/j.elerap.2025.101571","title":"A reinforcement learning-driven framework for the Q-commerce multi-product unit scheduling problem","year":2025,"lang":"en","type":"article","venue":"Electronic Commerce Research and Applications","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Laurentian University","funders":"Humanities and Social Science Fund of Ministry of Education of China; State Key Laboratory of Fluid Power and Mechatronic Systems; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Job shop scheduling; Scheduling (production processes); Variable neighborhood search; Reinforcement learning; Metaheuristic; Workload; Dynamic priority scheduling; Fair-share scheduling","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":[0.002482996,0.0007654765,0.002066863,0.0005564552,0.0005620246,0.001403414,0.003088733,0.001902472,0.00609638],"category_scores_gemma":[0.004574581,0.0006831803,0.0008995124,0.0008619632,0.001151833,0.00136985,0.001430693,0.002184545,0.000612971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001745681,"about_ca_system_score_gemma":0.002955872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01289505,"about_ca_topic_score_gemma":0.00987556,"domain_scores_codex":[0.9990082,0.0004410719,0.00003334191,0.0001664439,0.0002088615,0.0001420646],"domain_scores_gemma":[0.9980114,0.00127361,0.0001284442,0.00007618711,0.0003264846,0.0001838593],"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":[0.00004524729,0.00006589001,0.0001971411,0.00004786109,0.00002147061,0.00004788469,0.00002798694,0.9567423,0.0003277262,0.0284701,0.001124227,0.01288219],"study_design_scores_gemma":[0.00001069896,0.0000120762,0.00002164435,0.000002501917,0.000002717235,0.00000415646,0.000002526048,0.9938397,0.00003004447,0.005858545,0.0002128854,0.000002453724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007876854,0.0002411987,0.9879009,0.0003790074,0.0000657563,0.00008047861,0.00008043671,0.0001461441,0.003229245],"genre_scores_gemma":[0.7057124,0.0005665784,0.2831074,0.0002999636,0.000193425,0.0003773991,0.0002421611,0.0001319252,0.009368734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01289505,"threshold_uncertainty_score":0.02563995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04489443385723534,"score_gpt":0.3579772916523766,"score_spread":0.3130828577951412,"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."}}