{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00129061,0.0006948426,0.001168099,0.0004600539,0.0003471947,0.0006921395,0.001303951,0.002302317,0.003485818],"category_scores_gemma":[0.003858837,0.0005378849,0.0005010391,0.0003657707,0.0007706695,0.0009764038,0.001022879,0.002066624,0.0002152098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036699,"about_ca_system_score_gemma":0.001468265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01044079,"about_ca_topic_score_gemma":0.007653186,"domain_scores_codex":[0.9996604,0.0001511286,0.00001280512,0.00006789529,0.00004095147,0.00006681411],"domain_scores_gemma":[0.9974872,0.002100487,0.00008620568,0.00005259155,0.0001791107,0.00009444035],"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":[0.0000854829,0.00009853088,0.000500071,0.00004277536,0.00002191149,0.0000446593,0.00003207392,0.9695671,0.0003117054,0.004709061,0.0008624205,0.0237242],"study_design_scores_gemma":[0.000005255867,0.000006914079,0.00001907471,0.000001837881,0.000001823862,0.000001464353,0.000001411221,0.9989426,0.00003077474,0.0009633115,0.00002479545,7.653074e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1340327,0.0009137093,0.8557428,0.001782853,0.0001515535,0.00009935245,0.0001395127,0.0005614969,0.006576003],"genre_scores_gemma":[0.9483283,0.0001564289,0.04701624,0.0003348401,0.0000727227,0.0001071187,0.0001087826,0.00004359587,0.003831965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01044079,"threshold_uncertainty_score":0.02076006,"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."}}