{"id":"W2107741520","doi":"","title":"Weighted importance sampling for off-policy learning with linear function approximation","year":2014,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Weighting; Computer science; Importance sampling; Sampling (signal processing); Convergence (economics); Function (biology); Bridging (networking); Artificial intelligence; Mathematical optimization; Machine learning; Function approximation; Mathematics; Statistics; Artificial neural network","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":[0.003871777,0.001036859,0.001519142,0.0007723552,0.0004654666,0.0009972792,0.001582514,0.001238514,0.00247525],"category_scores_gemma":[0.01506721,0.0006548598,0.0006075407,0.0007096122,0.001491298,0.001559958,0.001529916,0.002218682,0.0004343321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001454449,"about_ca_system_score_gemma":0.001721152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003799199,"about_ca_topic_score_gemma":0.002948301,"domain_scores_codex":[0.9983357,0.0007954943,0.00007223223,0.0002013136,0.00046619,0.0001292071],"domain_scores_gemma":[0.9948004,0.003931496,0.0002417963,0.0003939313,0.0004869859,0.0001453537],"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":[0.0001379119,0.0001134671,0.0007565156,0.00009343355,0.00004127,0.00007150257,0.00005880834,0.8944612,0.00114141,0.04464915,0.0008608595,0.05761454],"study_design_scores_gemma":[0.000006589455,0.00001343828,0.00002424642,0.000003260468,0.000002175327,0.000005213354,0.000001674112,0.9923093,0.0001810288,0.007292121,0.0001590086,0.000001794239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005933413,0.0001403208,0.9926208,0.00008012487,0.00002959891,0.00003960179,0.00001124571,0.0001601256,0.0009846879],"genre_scores_gemma":[0.6960257,0.0003789738,0.2987357,0.0002635636,0.000102109,0.00041985,0.0001569149,0.0001849333,0.00373229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003871777,"threshold_uncertainty_score":0.02047622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02050125081507167,"score_gpt":0.2586979979424325,"score_spread":0.2381967471273608,"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."}}