{"id":"W4284893336","doi":"10.1109/icphm53196.2022.9815668","title":"Reinforcement Learning based on Stochastic Dynamic Programming for Condition-based Maintenance of Deteriorating Production Processes","year":2022,"lang":"en","type":"article","venue":"","topic":"Elevator Systems and Control","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Dynamic programming; Production (economics); Markov process; Preventive maintenance; Stochastic programming; Process (computing); Quality (philosophy); State (computer science); Mathematical optimization; Optimal maintenance; Q-learning; Reliability engineering; Artificial intelligence; Engineering; Mathematics; Algorithm","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":[0.0002265297,0.0001102962,0.0001472003,0.00008531509,0.0001910849,0.00001745368,0.0000650481,0.00001745722,0.00003242619],"category_scores_gemma":[0.0001468655,0.0001081923,0.00004254282,0.0001798572,0.00001292229,0.00004899948,0.000006504397,0.0001057809,7.129718e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001352378,"about_ca_system_score_gemma":0.00006661386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000813613,"about_ca_topic_score_gemma":0.00001339053,"domain_scores_codex":[0.9991834,0.00001854694,0.0002659212,0.0001539661,0.000186666,0.0001915519],"domain_scores_gemma":[0.9995753,0.00008646592,0.0001029951,0.000108553,0.00010342,0.00002331668],"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":[0.0000385121,0.00001714026,0.00006586347,0.0006408489,0.00001139651,3.454998e-7,0.00007339034,0.9913729,0.004883772,0.0000535354,0.00002139563,0.002820862],"study_design_scores_gemma":[0.0005706189,0.0004610931,0.00002066872,0.0001294885,0.00001268354,9.648638e-7,0.0004533175,0.9953128,0.002549064,0.000008261476,0.0003534734,0.0001275925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07155751,0.00003650855,0.9263837,0.0000810202,0.0002639938,0.001276782,0.000006542824,0.0002872961,0.0001066387],"genre_scores_gemma":[0.996978,1.125205e-7,0.001076893,0.00002427375,0.00002724472,0.00162139,0.00004224734,0.00002889996,0.0002009079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9254205,"threshold_uncertainty_score":0.4411954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00566666048657031,"score_gpt":0.2123191839889677,"score_spread":0.2066525235023974,"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."}}