{"id":"W191658262","doi":"","title":"{Toward Minimax Off-policy Value Estimation}","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Estimator; Minimax; Markov decision process; Multiplicative function; Mathematical optimization; Oracle; Computer science; Time horizon; Limit (mathematics); Sample size determination; Upper and lower bounds; Mathematics; Sample (material); Value (mathematics); Markov process; 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":[0.01404385,0.002073983,0.00355676,0.001524877,0.0009100023,0.003433095,0.002280192,0.003091802,0.004431943],"category_scores_gemma":[0.06357222,0.001100549,0.0008072635,0.001487048,0.003861881,0.004603599,0.003134237,0.00454172,0.0008970991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002563876,"about_ca_system_score_gemma":0.002528696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002247085,"about_ca_topic_score_gemma":0.001244083,"domain_scores_codex":[0.9928017,0.004987385,0.0002057915,0.0009208334,0.0007448291,0.0003394835],"domain_scores_gemma":[0.9558498,0.03919687,0.001821924,0.001410954,0.001265087,0.0004553628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006246804,0.0002605694,0.003637786,0.0004295434,0.0002362888,0.0002082736,0.0002065483,0.6809061,0.0008545367,0.2302415,0.004810543,0.07758363],"study_design_scores_gemma":[0.00003833509,0.0000758372,0.0002647117,0.00009280194,0.00001453421,0.00003449669,0.0000240798,0.8847965,0.0006087038,0.1133566,0.0006750371,0.00001825027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02885048,0.001123403,0.9618438,0.001956147,0.00007894573,0.0001917523,0.0002126094,0.0003580898,0.005384862],"genre_scores_gemma":[0.748836,0.001104621,0.2413628,0.001127627,0.0003069067,0.0007523631,0.0005857764,0.0002903809,0.005633518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01404385,"threshold_uncertainty_score":0.07427186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3651976247050544,"score_gpt":0.5253249721812989,"score_spread":0.1601273474762445,"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."}}