{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006400385,0.0001996109,0.0002096474,0.0002836304,0.0005195138,0.0009234643,0.0003451941,0.00009606953,8.648817e-7],"category_scores_gemma":[0.0002227671,0.0001652715,0.00004030316,0.0006244434,0.0000281705,0.005227198,0.00004706143,0.00021901,0.00002373346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001005635,"about_ca_system_score_gemma":0.0001149565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001019537,"about_ca_topic_score_gemma":4.99597e-7,"domain_scores_codex":[0.9982738,0.00005976248,0.0006617876,0.0002116586,0.0004620257,0.0003309453],"domain_scores_gemma":[0.9981285,0.00009550097,0.0008989705,0.0002714287,0.0005299504,0.00007563071],"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":[0.00002303111,0.000004573265,0.0005843919,0.0004843734,0.000008453634,5.330334e-8,0.0007866694,0.9183554,0.00007266143,0.01171112,0.00006408319,0.06790516],"study_design_scores_gemma":[0.000516156,0.0002619887,0.0002286585,0.0001289379,0.00000884387,0.00001668186,0.000121129,0.9689828,0.00009761469,0.00006849843,0.02936201,0.0002067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003359515,0.00004528818,0.9933459,0.0002346482,0.0003094954,0.0005470256,5.696735e-7,0.0005928659,0.001564703],"genre_scores_gemma":[0.9599105,0.000003391262,0.0388323,0.0003278566,0.0003431948,0.0001290645,0.000106194,0.00001915083,0.000328407],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956551,"threshold_uncertainty_score":0.8904988,"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."}}