{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.003593861,0.0003686303,0.0002932561,0.0006850472,0.00180029,0.0002632379,0.0007918457,0.00005060894,0.0006584849],"category_scores_gemma":[0.00005227717,0.0003871034,0.0003531658,0.0004595829,0.00004078359,0.0006399993,0.0007660318,0.001587455,0.0001443934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002347523,"about_ca_system_score_gemma":0.0001644763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001098556,"about_ca_topic_score_gemma":0.0002374202,"domain_scores_codex":[0.9953735,0.00006445141,0.00062884,0.0004950195,0.0007310154,0.002707171],"domain_scores_gemma":[0.9989852,0.00001697171,0.0005417846,0.0002982575,0.0001151354,0.00004262135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008566055,0.001974965,0.014611,0.0007951129,0.00257175,0.0001037308,0.0008515191,0.2950372,0.0003723683,0.5774423,0.01339581,0.09198754],"study_design_scores_gemma":[0.005407328,0.0002360291,0.0005076851,0.00002667151,0.0002550068,0.0000287774,0.01593894,0.3076749,0.000009620985,0.006682667,0.6625748,0.0006576075],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04133307,0.004903671,0.9269238,0.002726258,0.005847307,0.004869218,0.000001969019,0.000734991,0.01265978],"genre_scores_gemma":[0.9527847,0.001051583,0.001286037,0.003124859,0.001321245,0.0007421503,0.0001283455,0.000143614,0.03941749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9256377,"threshold_uncertainty_score":0.9998581,"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."}}