{"id":"W4404863321","doi":"10.1177/10591478241305863","title":"Multi-Agent Deep Reinforcement Learning for Multi-Echelon Inventory Management","year":2024,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Reinforcement learning; Computer science; Inventory management; Operations management; Reinforcement; Operations research; Business; Artificial intelligence; Psychology; Economics; Mathematics; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001343698,0.0007979692,0.0008858881,0.0003070368,0.0004290665,0.0006928602,0.00112224,0.001020801,0.001959006],"category_scores_gemma":[0.003749146,0.0004383967,0.0003959821,0.0003453462,0.0008558587,0.0009641938,0.001119336,0.001611317,0.000221613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001388052,"about_ca_system_score_gemma":0.002048981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01074851,"about_ca_topic_score_gemma":0.009288794,"domain_scores_codex":[0.999592,0.0001451125,0.00001710344,0.00007916325,0.00007797096,0.00008867572],"domain_scores_gemma":[0.9985689,0.0008475999,0.0001710382,0.0001019839,0.0001882256,0.0001222604],"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":[0.00002014829,0.00002064796,0.0002373348,0.00001191955,0.000009997315,0.00001390271,0.00001058884,0.9926979,0.0002089753,0.001484527,0.0001564747,0.00512751],"study_design_scores_gemma":[0.000002503806,0.000005551791,0.0000157341,8.417406e-7,0.000001117255,9.806122e-7,0.000001462107,0.9992126,0.00006235357,0.0006562119,0.00003986676,7.283455e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09284659,0.000358177,0.9010907,0.0005970785,0.0000745422,0.00006287261,0.00005479633,0.00066726,0.004247971],"genre_scores_gemma":[0.945897,0.00008670704,0.05212251,0.0001378005,0.00001912232,0.00006359262,0.00005245694,0.00003636491,0.001584477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01074851,"threshold_uncertainty_score":0.0213719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02766765650376406,"score_gpt":0.2651066508008719,"score_spread":0.2374389942971078,"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."}}