{"id":"W4405888278","doi":"10.1177/00375497241299054","title":"Combining simulation and reinforcement learning to reduce food waste in food retail","year":2024,"lang":"en","type":"article","venue":"SIMULATION","topic":"Supply Chain and Inventory Management","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Food waste; Computer science; Baseline (sea); Reinforcement; Operations research; Artificial intelligence; Engineering; Waste management","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":[],"consensus_categories":[],"category_scores_codex":[0.0004307846,0.0001475335,0.0001278711,0.0005275499,0.0001193672,0.000391477,0.00007160809,0.00005038813,0.0001044877],"category_scores_gemma":[0.0001290742,0.0001561199,0.00003552192,0.0005771591,0.00001222671,0.0009819036,0.0001369148,0.0001320708,0.00007980346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007882887,"about_ca_system_score_gemma":0.000007410476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003218992,"about_ca_topic_score_gemma":0.0000324195,"domain_scores_codex":[0.9988996,0.0000153928,0.0003046496,0.0003151061,0.0002449194,0.0002203195],"domain_scores_gemma":[0.9996579,0.00008472386,0.00006697695,0.0001241972,0.00005053178,0.0000156922],"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":[0.00002931958,0.0000105366,0.001426159,0.0001759877,0.00001695301,0.000001944897,0.0004832967,0.9710698,0.00009459992,0.008035048,0.00007707257,0.01857929],"study_design_scores_gemma":[0.0004145938,0.00008062714,0.001113821,0.0001923522,0.00001731675,7.998791e-8,0.0008195133,0.9502029,0.00003399894,0.00107627,0.04587071,0.0001778562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9763969,0.000156632,0.009938085,0.0006101901,0.0005184042,0.000623216,3.569928e-7,0.0002358768,0.01152035],"genre_scores_gemma":[0.9983454,0.000002475444,0.00003922892,0.0004565575,0.0004386746,0.00002255884,0.00004173558,0.00002833355,0.0006250857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04579364,"threshold_uncertainty_score":0.6366383,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04847384823811063,"score_gpt":0.2701677477949835,"score_spread":0.2216938995568729,"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."}}