{"id":"W4389139904","doi":"10.2139/ssrn.4648081","title":"An Adaptable Fuzzy Reinforcement Learning Method for Non-Stationary Environments","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Elevator Systems and Control","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Fuzzy logic; Artificial intelligence; Engineering; Structural engineering","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":[0.0006988405,0.0005832954,0.0008043897,0.000331428,0.00034905,0.0005108804,0.001207556,0.0009349052,0.002838117],"category_scores_gemma":[0.001341706,0.0002826257,0.0004599807,0.0002753915,0.0005126089,0.000549169,0.0009460011,0.0008550924,0.0003316856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004933007,"about_ca_system_score_gemma":0.0006680937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006080646,"about_ca_topic_score_gemma":0.004720636,"domain_scores_codex":[0.9997559,0.00006469193,0.00001275666,0.00005900657,0.00007456797,0.00003299361],"domain_scores_gemma":[0.9995804,0.0002013036,0.00003274927,0.00002970349,0.0001225963,0.00003319851],"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":[0.0001195762,0.00007492887,0.0003094322,0.00008551183,0.0000531266,0.00008881959,0.00007437265,0.8459414,0.005212168,0.007692873,0.0009212169,0.1394265],"study_design_scores_gemma":[0.000007121542,0.00002284564,0.00002887643,0.000002321505,0.000003739635,0.000006851653,0.000001895296,0.998969,0.000199424,0.0005983844,0.0001572466,0.00000237593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009954529,0.0001147028,0.9883023,0.00004812623,0.00004765499,0.00002815393,0.000009632547,0.0001709647,0.001323997],"genre_scores_gemma":[0.7675787,0.0001716847,0.2258484,0.0001066693,0.00007809252,0.0001763357,0.00004678744,0.00006919498,0.005924199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006080646,"threshold_uncertainty_score":0.0120905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01195887957372108,"score_gpt":0.2561132737417993,"score_spread":0.2441543941680782,"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."}}