{"id":"W4417338422","doi":"10.1109/icmlc66258.2025.11280010","title":"Multi-Strategy Reinforcement Learning Simulation Based on Value Model for Petroleum Supply Chain","year":2025,"lang":"","type":"article","venue":"","topic":"Process Optimization and Integration","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro-Canada","funders":"","keywords":"Reinforcement learning; Scheduling (production processes); Supply chain; Process (computing); Resource (disambiguation); Value (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":[0.0003328903,0.0003770194,0.0002879332,0.0004427954,0.0002844271,0.0001931878,0.0001550887,0.0002586902,0.0002800032],"category_scores_gemma":[0.000350886,0.0003952912,0.0001614468,0.0003009073,0.00002013381,0.0003358302,0.00001807027,0.0003238906,0.00002130157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003585459,"about_ca_system_score_gemma":0.0002200521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001815836,"about_ca_topic_score_gemma":0.0000131376,"domain_scores_codex":[0.9982327,0.0000413728,0.0006708512,0.0004072896,0.0002418354,0.0004059852],"domain_scores_gemma":[0.9990341,0.0002488161,0.000110408,0.0002430303,0.0002742137,0.00008939761],"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":[0.000162326,0.00008113892,0.00003190952,0.0002800949,0.00004035112,1.356377e-7,0.0001502846,0.9831741,0.0004335063,0.01266572,0.0001800574,0.002800363],"study_design_scores_gemma":[0.002576784,0.0002395405,0.00001875501,0.0002243049,0.00005477249,2.903308e-8,0.0001373341,0.9934022,0.002226746,0.00009479056,0.0006718721,0.0003528871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001553193,0.00006535854,0.9819871,0.0003346133,0.0002731362,0.0008412075,0.00001044473,0.000303861,0.01602892],"genre_scores_gemma":[0.9354513,0.00004713414,0.02784634,0.0006043595,0.00004118818,0.0001623461,0.0002950762,0.00004769762,0.0355046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9541408,"threshold_uncertainty_score":0.9998499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02333807197868211,"score_gpt":0.2817819626914458,"score_spread":0.2584438907127637,"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."}}