{"id":"W3101675824","doi":"","title":"CoinDICE: Off-Policy Confidence Interval Estimation","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Confidence interval; Reinforcement learning; Computer science; Embedding; Bellman equation; Mathematical optimization; Function (biology); Confidence region; Algorithm; Mathematics; Applied mathematics; Statistics; Artificial intelligence","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":[0.0161446,0.00170037,0.003182671,0.00167999,0.0006244658,0.003216287,0.004584654,0.002886911,0.003531428],"category_scores_gemma":[0.1150313,0.001212201,0.001000299,0.001381742,0.002846551,0.004399699,0.004872076,0.006036969,0.0006443906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002093356,"about_ca_system_score_gemma":0.00283108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003358547,"about_ca_topic_score_gemma":0.00234656,"domain_scores_codex":[0.9908609,0.00435506,0.0004444509,0.00155083,0.002223681,0.0005649171],"domain_scores_gemma":[0.9097375,0.07493442,0.004507284,0.005442101,0.004117314,0.001261374],"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":[0.000546149,0.0002464021,0.004323005,0.0002653845,0.0001885487,0.0001559782,0.0001994721,0.79034,0.001273977,0.05942087,0.002535724,0.1405045],"study_design_scores_gemma":[0.00002788709,0.00005470681,0.0001684051,0.00002800446,0.000009630941,0.00003086587,0.000008603024,0.9818,0.0009707442,0.016548,0.0003400541,0.00001307313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01168864,0.0004268807,0.985535,0.0002818293,0.00004567411,0.00007465205,0.00007320975,0.0008015578,0.001072542],"genre_scores_gemma":[0.6133296,0.0003177189,0.3829932,0.0004155631,0.0001037081,0.0003534736,0.0004508888,0.0004673217,0.001568555],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0161446,"threshold_uncertainty_score":0.08538187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07032887715500136,"score_gpt":0.2019229274474927,"score_spread":0.1315940502924913,"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."}}