{"id":"W4313162358","doi":"10.2139/ssrn.4262186","title":"Multi-Agent Deep Reinforcement Learning for Multi-Echelon Inventory Management","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Supply Chain and Inventory Management","field":"Business, Management and Accounting","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Reinforcement; Inventory management; Business; Artificial intelligence; Computer science; Operations management; Engineering; Psychology; Social psychology","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":[0.001474688,0.0008652499,0.001560784,0.0005106486,0.0005306175,0.0009618024,0.00145538,0.001914183,0.003213613],"category_scores_gemma":[0.004134151,0.0007358778,0.0005401184,0.0004526868,0.0008998485,0.001018162,0.001464143,0.001970676,0.0003795251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001459003,"about_ca_system_score_gemma":0.00158544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01581361,"about_ca_topic_score_gemma":0.01433184,"domain_scores_codex":[0.9996141,0.0001320132,0.0000208659,0.00007967497,0.00006085684,0.0000925327],"domain_scores_gemma":[0.9977359,0.001587594,0.0001868169,0.00008741582,0.0002515645,0.0001506963],"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":[0.00004754142,0.0000419003,0.0003215748,0.00002071128,0.00001839106,0.00002622551,0.00001596783,0.9861924,0.0001883852,0.001378193,0.000390808,0.01135785],"study_design_scores_gemma":[0.000002517961,0.000005367006,0.00001702106,0.000001241863,0.000001148098,0.000001139045,0.000001039347,0.9994892,0.00002667619,0.0004328976,0.00002097468,7.951176e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1029871,0.0009675666,0.8893307,0.0009010842,0.0001652114,0.00007763591,0.0001564193,0.0009283414,0.004485988],"genre_scores_gemma":[0.956585,0.0001283166,0.03964068,0.0001711233,0.0000491379,0.00008279215,0.0001066686,0.00004136993,0.003194797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01581361,"threshold_uncertainty_score":0.03144312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0279344231893986,"score_gpt":0.2478275419284759,"score_spread":0.2198931187390774,"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."}}