{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007052846,0.000158719,0.0001874911,0.0001933644,0.0001171643,0.0002708101,0.0006519499,0.000058287,0.00004710166],"category_scores_gemma":[0.0003291873,0.0001510083,0.00006946205,0.0002527537,0.00004121259,0.0007084053,0.0002216048,0.0004003306,0.00006597177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004491041,"about_ca_system_score_gemma":0.00004822283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005299484,"about_ca_topic_score_gemma":0.0000387902,"domain_scores_codex":[0.9985442,0.00003313496,0.0004369816,0.0003143931,0.0002604686,0.0004108094],"domain_scores_gemma":[0.9990759,0.0002023099,0.0001712236,0.0003714172,0.00009933516,0.00007974451],"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":[0.000008166896,0.00001332239,0.001121734,0.0000155432,0.000009968058,0.000003549139,0.0007654837,0.9331657,0.0008692686,0.02860728,0.0001982119,0.03522178],"study_design_scores_gemma":[0.000816273,0.000167572,0.0006852244,0.00001749834,0.000002684767,0.000005648065,0.00003678511,0.9910952,0.001584015,0.000842525,0.004554767,0.0001917458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00974362,0.000001791764,0.9836797,0.0003096307,0.0006215293,0.0004325028,2.182089e-7,0.0002520289,0.004958996],"genre_scores_gemma":[0.6239246,0.00000213286,0.3702175,0.0001677058,0.00003535036,0.00004355845,0.00001221826,0.00001319253,0.005583813],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6141809,"threshold_uncertainty_score":0.6157941,"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."}}