{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001041667,0.0001270183,0.0001321772,0.0001094107,0.0001175701,0.0001036038,0.001073187,0.00005771015,0.00004272384],"category_scores_gemma":[0.0001847841,0.0001494246,0.00006456151,0.0008904632,0.00008178687,0.0008156629,0.0003906807,0.0001823452,0.000597482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009113267,"about_ca_system_score_gemma":0.0001307088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003423336,"about_ca_topic_score_gemma":0.000001647079,"domain_scores_codex":[0.9990504,0.00006363427,0.0001395433,0.0004099747,0.00009915674,0.0002372249],"domain_scores_gemma":[0.9991456,0.00007995684,0.0001334472,0.0003829654,0.000074645,0.0001833431],"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":[0.000007143488,0.000006052388,0.0005617992,0.00001004122,0.00001086932,0.00005658178,0.0003756426,0.7262908,0.00004340593,0.2716058,0.0002778109,0.0007539979],"study_design_scores_gemma":[0.0003161127,0.0001189033,0.0006363726,0.0000161027,0.000009692705,0.000004191549,0.00005335715,0.9958774,0.0001924407,0.00131284,0.001305559,0.0001570038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01739273,0.000007789095,0.9767696,0.001123228,0.0001029243,0.0001032997,6.904588e-7,0.0002621728,0.004237577],"genre_scores_gemma":[0.99426,0.000021682,0.003824741,0.000999577,0.00005241768,1.545844e-7,0.000002712552,0.000007209543,0.0008314733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9768673,"threshold_uncertainty_score":0.7679621,"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."}}