{"id":"W2163126463","doi":"","title":"Online Discovery and Learning of Predictive State Representations","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Machine learning; Outcome (game theory); Artificial intelligence; Gradient descent; State (computer science); Current (fluid); Algorithm; Monte Carlo method; Data mining; Artificial neural network; Mathematics","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":[0.003230471,0.001142196,0.001893662,0.001374809,0.0006020138,0.001331214,0.002922654,0.001847864,0.001875511],"category_scores_gemma":[0.02122235,0.0009219943,0.0007481032,0.001038852,0.001883355,0.003641349,0.001965031,0.002964907,0.0004471036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001604535,"about_ca_system_score_gemma":0.002282707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005235604,"about_ca_topic_score_gemma":0.004391365,"domain_scores_codex":[0.9982046,0.0006456233,0.0001242508,0.0004419242,0.0004049697,0.0001786853],"domain_scores_gemma":[0.9837664,0.01219103,0.001182803,0.001318174,0.001233649,0.0003078702],"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":[0.0002025805,0.0001750587,0.003066506,0.0001286324,0.00007280242,0.0001396482,0.0001368145,0.8506566,0.001153349,0.02782316,0.002649492,0.1137953],"study_design_scores_gemma":[0.000009710092,0.00001299594,0.000092716,0.000004765291,0.000003892337,0.000009655426,0.000004618422,0.9898536,0.0002985472,0.009588757,0.0001167257,0.000004034673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03292457,0.0001797847,0.9641674,0.0004334172,0.0000280094,0.00007524841,0.0001519098,0.001037008,0.001002714],"genre_scores_gemma":[0.7637321,0.0001920209,0.233094,0.0002336863,0.0000546264,0.0003026404,0.0007161121,0.0001377735,0.001537047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005235604,"threshold_uncertainty_score":0.01708454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397289807407894,"score_gpt":0.270802323912168,"score_spread":0.256829425838089,"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."}}