{"id":"W4385484908","doi":"10.1109/icphm57936.2023.10194057","title":"A Reinforcement Learning Algorithm for Optimal Dynamic Policies of Joint Condition-based Maintenance and Condition-based Production","year":2023,"lang":"en","type":"article","venue":"","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Markov decision process; Reinforcement learning; Production (economics); Computer science; Mathematical optimization; Dynamic programming; Q-learning; Time horizon; Production planning; Markov process; Scheduling (production processes); Algorithm; Mathematics; Artificial intelligence; Economics","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":[0.001627506,0.0008886508,0.001332401,0.0005480946,0.0005193244,0.0007233993,0.001285563,0.001211089,0.002831178],"category_scores_gemma":[0.004790571,0.0004526048,0.0004329556,0.0004055595,0.0007804352,0.0008052756,0.0008738734,0.001799924,0.0004207188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001319408,"about_ca_system_score_gemma":0.002572291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009250997,"about_ca_topic_score_gemma":0.005257255,"domain_scores_codex":[0.9995034,0.0001476695,0.00002686319,0.0001206632,0.0001269462,0.00007462312],"domain_scores_gemma":[0.9985876,0.0009391423,0.0001287743,0.00004109113,0.0002322084,0.00007111159],"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":[0.00006785817,0.00008191833,0.0004204024,0.00004525276,0.00002486969,0.00004725784,0.00004773932,0.9273487,0.0009044383,0.009312565,0.001047891,0.06065107],"study_design_scores_gemma":[0.0000150249,0.00002095108,0.00003199067,0.000004730798,0.000002637469,0.000006926945,0.000002287846,0.9983029,0.0001274537,0.001278502,0.000203598,0.000003019355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008370586,0.0001284352,0.9888368,0.0001346194,0.00003018806,0.00007947161,0.00002180902,0.0003790298,0.002019109],"genre_scores_gemma":[0.5536039,0.0002119055,0.4419104,0.0001828536,0.00005345369,0.0005580886,0.0001335479,0.000113375,0.003232511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009250997,"threshold_uncertainty_score":0.01839429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0082320604232123,"score_gpt":0.2321525028041775,"score_spread":0.2239204423809652,"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."}}