{"id":"W4406331954","doi":"10.1080/15732479.2025.2451277","title":"Reliability-based reinforcement learning driven maintenance policy optimization","year":2025,"lang":"en","type":"article","venue":"Structure and Infrastructure Engineering","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reliability (semiconductor); Reinforcement; Reliability engineering; Reinforcement learning; Computer science; Preventive maintenance; Engineering; Structural engineering; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007402949,0.0003088251,0.0002663594,0.0003145509,0.0001161959,0.00007980073,0.0001420664,0.0002136814,0.00005319907],"category_scores_gemma":[0.0002072036,0.0002888307,0.00005777134,0.0005777846,0.00005638869,0.0002387719,0.00004344737,0.0004556115,6.063035e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002207261,"about_ca_system_score_gemma":0.00006293656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008822135,"about_ca_topic_score_gemma":0.000001304939,"domain_scores_codex":[0.9988506,0.00001599293,0.0003312332,0.000292749,0.0001351767,0.000374251],"domain_scores_gemma":[0.9994648,0.00004551426,0.00004116323,0.0002661007,0.00009742381,0.00008499884],"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":[0.00001027145,0.000001384951,0.000366104,0.0002714634,0.00002425856,8.086713e-7,0.00008777665,0.9921646,0.002312231,0.002649293,0.0003225301,0.001789316],"study_design_scores_gemma":[0.0004370766,0.0000256066,0.001932561,0.0001230926,0.00001937871,0.000003485282,0.00002520777,0.9883632,0.002264225,0.0004642676,0.006082745,0.00025915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02525456,0.0001393676,0.9713886,0.0001517294,0.000556831,0.0003042759,0.00000773975,0.000551928,0.001645007],"genre_scores_gemma":[0.9534597,0.000153204,0.04589887,0.0001469039,0.0001156707,0.00001666283,0.0000671033,0.00003677171,0.0001050888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9282052,"threshold_uncertainty_score":0.9999564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.001327953338515625,"score_gpt":0.1783856397812691,"score_spread":0.1770576864427535,"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."}}