{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002668707,0.0001634536,0.00009616483,0.0002684009,0.000275977,0.0002279644,0.00006575089,0.00003751732,0.00004772645],"category_scores_gemma":[0.00001477089,0.0001666979,0.00004594974,0.0002358106,0.00002037883,0.00020559,0.00004646369,0.0001101727,0.00005689861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001187208,"about_ca_system_score_gemma":0.000004078575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002509941,"about_ca_topic_score_gemma":0.00001267528,"domain_scores_codex":[0.999061,0.00001751694,0.0002538575,0.0003458011,0.0001308876,0.0001909263],"domain_scores_gemma":[0.9997122,0.000004419592,0.00001127082,0.0001639835,0.00004622446,0.00006194845],"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":[0.000003005398,0.00003483783,0.00001262418,0.0004989154,0.0001683113,0.000002624167,0.0005619128,0.9637823,0.00005067791,0.002586615,0.0006108852,0.03168733],"study_design_scores_gemma":[0.0003247546,0.00002053076,0.00008928619,0.00008083156,0.00008289734,0.000002491177,0.0008170636,0.9636283,0.0002672157,0.000007924787,0.03448579,0.0001929043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007517029,0.001810458,0.9926431,0.0003570213,0.001813121,0.001062842,7.078535e-7,0.0007359812,0.0008250191],"genre_scores_gemma":[0.2238315,0.006266463,0.721584,0.000138692,0.000333002,0.001409759,0.0001664202,0.00008873949,0.0461815],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2710592,"threshold_uncertainty_score":0.6797743,"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."}}