{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003107789,0.0004281915,0.0005597936,0.0003618944,0.0004130906,0.0007128199,0.001199139,0.0007828966,0.001010721],"category_scores_gemma":[0.01436337,0.0002866889,0.0002227251,0.000299764,0.0007176477,0.001776841,0.0009894025,0.000849752,0.00011993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005098989,"about_ca_system_score_gemma":0.0008864627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001904646,"about_ca_topic_score_gemma":0.002538538,"domain_scores_codex":[0.9989229,0.000435689,0.00005599976,0.0001254597,0.0003093767,0.0001505517],"domain_scores_gemma":[0.9862121,0.01164579,0.0006304651,0.0004877066,0.0006616477,0.0003621974],"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":[0.0009435568,0.0004759911,0.009158223,0.0002509291,0.00009321164,0.0001382274,0.0004131864,0.6841502,0.01159867,0.02163182,0.0005999993,0.2705459],"study_design_scores_gemma":[0.00003505067,0.0002301666,0.0007772288,0.000008115297,0.00001299448,0.00005278607,0.0000420952,0.9928247,0.002250384,0.003501331,0.000255842,0.000009357723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3461737,0.0004732854,0.648441,0.0003308753,0.00003069931,0.00009195851,0.00001683458,0.0002616315,0.004179953],"genre_scores_gemma":[0.9295375,0.0001029049,0.0694991,0.00006600086,0.00001096037,0.00005323624,0.00001351669,0.00003128949,0.0006855465],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003107789,"threshold_uncertainty_score":0.01643574,"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."}}