{"id":"W2131056066","doi":"10.1109/ijcnn.2008.4634208","title":"Tradeoff between exploration and exploitation of OQ(λ) with non-Markovian update in dynamic environments","year":2008,"lang":"en","type":"article","venue":"","topic":"Elevator Systems and Control","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lambda; Computer science; Algorithm; Markov process; Mathematics; Mathematical optimization; Physics; Statistics","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":[0.00005784019,0.00009632883,0.0001608772,0.00007842367,0.00002225203,0.000005507385,0.00003750136,0.00004384527,0.0000101678],"category_scores_gemma":[0.000001933502,0.00008546839,0.00001291799,0.0000828041,0.00002242779,0.0002818406,0.000004775797,0.00005537574,0.000008255536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003164251,"about_ca_system_score_gemma":0.000005102983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000353459,"about_ca_topic_score_gemma":0.0002305454,"domain_scores_codex":[0.9994516,0.00001366212,0.0002093244,0.0001060415,0.0001078955,0.0001114191],"domain_scores_gemma":[0.9998025,0.00001806648,0.00003002543,0.0001092938,0.000004273099,0.00003585679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002490775,0.0002864075,0.6091208,0.0007731175,0.0005704919,0.00004276287,0.02605686,0.06323788,0.1965317,0.0007758107,0.0005711509,0.1017839],"study_design_scores_gemma":[0.005908351,0.0003386492,0.9052258,0.0002491672,0.00007047279,0.00001989118,0.001943324,0.07460761,0.00705873,0.0004116758,0.003234784,0.000931588],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9460639,0.00007325554,0.05322579,0.00005312051,0.00002111183,0.0001760944,0.000004299729,0.0000282009,0.0003541682],"genre_scores_gemma":[0.9985465,0.0001052908,0.001123907,0.000005649123,0.00001324284,0.00003370132,0.00001932774,0.00001829983,0.0001341253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2961049,"threshold_uncertainty_score":0.34853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024050949748049,"score_gpt":0.1853958431772147,"score_spread":0.1751553336797342,"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."}}