{"id":"W3123052397","doi":"10.1057/s41272-020-00275-x","title":"Deep reinforcement learning in seat inventory control problem: an action generation approach","year":2021,"lang":"en","type":"article","venue":"Journal of Revenue and Pricing Management","topic":"Supply Chain and Inventory Management","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Heuristic; Mathematical optimization; Set (abstract data type); Action (physics); Space (punctuation); Artificial intelligence; Operations research; Mathematics","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":[0.001118466,0.0001481508,0.0002381194,0.0004066705,0.0001411827,0.0002277246,0.0001235836,0.00004497553,0.00003470989],"category_scores_gemma":[0.00002839463,0.0001446093,0.00006934217,0.0003307737,0.0000181975,0.001040367,0.0001002637,0.0002278697,0.000006711678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001072873,"about_ca_system_score_gemma":0.00001507522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005881193,"about_ca_topic_score_gemma":0.00007070852,"domain_scores_codex":[0.9986798,0.00007115882,0.0004783783,0.0002118037,0.0003407718,0.0002180654],"domain_scores_gemma":[0.9992526,0.00001007003,0.0004485863,0.0001421804,0.000121637,0.00002489043],"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":[0.0003089444,0.0008932742,0.06937401,0.003367844,0.0006496811,0.0007228597,0.001827276,0.6051587,0.002793828,0.02325578,0.014984,0.2766638],"study_design_scores_gemma":[0.006792546,0.000234629,0.0186195,0.0006058388,0.0006051913,0.00006160057,0.005652606,0.5710088,0.0001406239,0.002717901,0.3928305,0.0007302322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7624933,0.003877152,0.175033,0.003185213,0.002435167,0.001859636,6.650728e-7,0.00009790436,0.0510179],"genre_scores_gemma":[0.9949336,0.0005242099,0.000934626,0.001288998,0.001018742,0.00001688269,0.00002195662,0.00001993573,0.00124105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3778465,"threshold_uncertainty_score":0.5896996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03147514551223286,"score_gpt":0.238186230864156,"score_spread":0.2067110853519231,"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."}}