{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002536241,0.0001329172,0.0001813754,0.0001826025,0.00009826438,0.00002179725,0.00004054152,0.00006187616,0.000041737],"category_scores_gemma":[0.0001542749,0.000128653,0.0000611089,0.0002509071,0.0001003359,0.0001242419,0.000008856314,0.00008268064,0.000005583046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009390262,"about_ca_system_score_gemma":0.00003768484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000271669,"about_ca_topic_score_gemma":0.000007459313,"domain_scores_codex":[0.999138,0.00001499504,0.0002997859,0.0001858646,0.0001225749,0.0002388079],"domain_scores_gemma":[0.9995025,0.00008173961,0.00007023763,0.0001294255,0.0001739357,0.00004209624],"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":[0.00001126038,0.00001061338,0.00002272637,0.000244645,0.00001611547,3.292371e-7,0.00008778111,0.9924378,0.003628863,0.0003860071,0.001061192,0.00209268],"study_design_scores_gemma":[0.000625808,0.0001354736,0.0004952965,0.0001012563,0.0000165371,0.000001052512,0.0003016296,0.9822689,0.0153175,0.0001664983,0.0004241977,0.0001458423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04300031,0.0000159985,0.9548668,0.0005349152,0.0001985159,0.000666943,0.00003810554,0.0004426473,0.0002358256],"genre_scores_gemma":[0.9729038,0.00005890081,0.02527361,0.00005380477,0.00002824968,0.0002398635,0.0006195336,0.0000293037,0.0007928904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9299035,"threshold_uncertainty_score":0.5246319,"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."}}