{"id":"W2105114545","doi":"","title":"Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Bootstrapping (finance); Markov decision process; Computer science; Machine learning; Artificial intelligence; Confidence interval; Value (mathematics); Algorithm; Markov process; Statistics; Mathematics; Econometrics","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":[0.01062816,0.001343782,0.001745475,0.001822855,0.0005605264,0.002494093,0.002853889,0.001779483,0.00318793],"category_scores_gemma":[0.1034777,0.0007709941,0.0009818746,0.00150135,0.002334812,0.003721207,0.002571892,0.0051182,0.0007092691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001910079,"about_ca_system_score_gemma":0.001342329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00363801,"about_ca_topic_score_gemma":0.001439517,"domain_scores_codex":[0.9949126,0.002504525,0.0003883963,0.0007308437,0.001220018,0.0002435169],"domain_scores_gemma":[0.919885,0.06983439,0.002906842,0.003065308,0.003504609,0.0008039179],"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":[0.0002577494,0.000095321,0.00188103,0.0001999181,0.00007642811,0.00007482716,0.0002371475,0.8490941,0.0008626158,0.06904817,0.0009687145,0.077204],"study_design_scores_gemma":[0.00001378695,0.00002591036,0.00008906359,0.00002415866,0.000005555406,0.00001125623,0.000007234478,0.975401,0.0003523566,0.023858,0.0002027133,0.000008938629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003343344,0.0002241655,0.9955761,0.0000802334,0.00001849487,0.00002353626,0.00002150184,0.000298407,0.0004142841],"genre_scores_gemma":[0.4557754,0.0005582791,0.5416505,0.0001549353,0.0001122543,0.0003862028,0.0002747453,0.0002992496,0.0007884523],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01062816,"threshold_uncertainty_score":0.05620778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01229210433285551,"score_gpt":0.2686448487087605,"score_spread":0.256352744375905,"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."}}