{"id":"W2398850217","doi":"","title":"Off-policy learning based on weighted importance sampling with linear computational complexity","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Component (thermodynamics); Computational complexity theory; Computer science; Sampling (signal processing); Measure (data warehouse); Stochastic gradient descent; Importance sampling; Algorithm; Function (biology); Mathematical optimization; Artificial intelligence; Mathematics; Machine learning; Data mining; Artificial neural network; Statistics; Monte Carlo method","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":[0.0009793651,0.0002772136,0.00029904,0.0003877211,0.0002284174,0.0001766961,0.0007577104,0.00008302501,0.00003403316],"category_scores_gemma":[0.000579313,0.0002406302,0.0000614802,0.001429596,0.0002140437,0.0002070034,0.0001078717,0.000715045,0.0001335582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002462965,"about_ca_system_score_gemma":0.0005434809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008314554,"about_ca_topic_score_gemma":0.0002953709,"domain_scores_codex":[0.9973401,0.00025819,0.0005341959,0.000659847,0.0006976792,0.0005100168],"domain_scores_gemma":[0.9983453,0.0004829309,0.000213377,0.00042604,0.0002949243,0.0002373943],"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":[0.00008046426,0.0001284483,0.001997954,0.000005992463,0.000004750284,0.00002566432,0.000670577,0.8587947,0.000005049031,0.08123843,0.00001486686,0.05703305],"study_design_scores_gemma":[0.0001276778,0.0003734022,0.0004008528,0.00007288471,0.000002054605,0.000007615158,0.0001707732,0.9410805,0.000145514,0.05623412,0.001090161,0.0002944139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03107515,0.0000260963,0.9631496,0.0035784,0.0001839313,0.0002105229,0.000004229126,0.0002870912,0.001484941],"genre_scores_gemma":[0.8723392,0.000002094098,0.1265895,0.0007171653,0.0002279944,0.00001607992,0.00003545838,0.00001792476,0.0000545711],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8412641,"threshold_uncertainty_score":0.9812614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09631687283916708,"score_gpt":0.3443424134911935,"score_spread":0.2480255406520264,"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."}}