{"id":"W2952662670","doi":"10.48550/arxiv.1906.04328","title":"Importance Resampling for Off-policy Prediction","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Resampling; Consistency (knowledge bases); Variance (accounting); Computer science; Reinforcement learning; Sampling (signal processing); Jackknife resampling; Function (biology); Statistics; Artificial intelligence; Machine learning; Econometrics; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003324009,0.0002894708,0.0003038401,0.0003453507,0.0001672066,0.0001658551,0.001871363,0.0002815784,0.000008035873],"category_scores_gemma":[0.00015645,0.0003568034,0.0002303697,0.0004730548,0.00005590347,0.0004325869,0.001525293,0.0005182231,0.00006851694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004312626,"about_ca_system_score_gemma":0.0004639052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003991971,"about_ca_topic_score_gemma":0.000004526296,"domain_scores_codex":[0.9980398,0.00005302588,0.0002820548,0.00106796,0.00012251,0.0004346454],"domain_scores_gemma":[0.9974092,0.0001731627,0.0004500771,0.001629915,0.0002183022,0.000119297],"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":[0.00001545959,0.00001222111,0.004798691,0.0001044921,0.00005130505,0.00001046517,0.0000882224,0.9087995,0.0000109245,0.08523894,0.000578708,0.0002910216],"study_design_scores_gemma":[0.0004177455,0.00008041999,0.001712596,0.00009786605,0.00003595964,0.000001814702,0.00001540288,0.9844982,0.00003181753,0.008042074,0.004754392,0.0003116862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0158975,0.00004210594,0.9782839,0.0001212907,0.001125017,0.0006943757,0.00002122891,0.0003748256,0.003439798],"genre_scores_gemma":[0.9801338,0.0002616565,0.01059679,0.0001510686,0.0003056418,0.000002977061,0.00006433404,0.00003114818,0.008452608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9676871,"threshold_uncertainty_score":0.9998884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08829860924234678,"score_gpt":0.2152403378248559,"score_spread":0.1269417285825091,"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."}}