{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007157346,0.0005158102,0.0006095573,0.0003413862,0.0003914262,0.0006445703,0.0008225858,0.0008128803,0.00169232],"category_scores_gemma":[0.001798009,0.0002269339,0.0004381234,0.0003308084,0.0007056269,0.00065851,0.0007662293,0.0008469219,0.0001004568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001020807,"about_ca_system_score_gemma":0.0009171225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01335426,"about_ca_topic_score_gemma":0.006705778,"domain_scores_codex":[0.9996716,0.0001721725,0.00001276951,0.00004025371,0.00005384651,0.0000493625],"domain_scores_gemma":[0.9991161,0.000581852,0.0001004391,0.0000340921,0.00009782713,0.00006978985],"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":[0.00001360356,0.00001008194,0.0001948093,0.000005587918,0.00000394908,0.00002021494,0.00001074104,0.9965064,0.0001364191,0.002363849,0.00003351824,0.0007007604],"study_design_scores_gemma":[0.000003440576,0.000007680323,0.00002511601,7.254913e-7,0.000001063313,0.000001177023,0.000002394961,0.99932,0.00005365414,0.0005476575,0.00003590819,0.000001120235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3526387,0.0003815872,0.6307968,0.0006339251,0.00006328175,0.0001516447,0.0001366621,0.0003324371,0.01486513],"genre_scores_gemma":[0.9857067,0.00007818549,0.01298551,0.00002355248,0.000004757108,0.00007663311,0.00002934762,0.00000834405,0.001086969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01335426,"threshold_uncertainty_score":0.02655303,"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."}}