{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001160198,0.00005405871,0.00007572986,0.00005921766,0.00005953322,0.00006525414,0.0001780861,0.00001414563,0.00001106457],"category_scores_gemma":[0.00009919722,0.0000473901,0.00001807075,0.000135953,0.00004482288,0.0008338679,0.0001926996,0.0001231091,0.000004461365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001249813,"about_ca_system_score_gemma":0.00002312124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002938448,"about_ca_topic_score_gemma":0.00000533193,"domain_scores_codex":[0.9993716,0.00004305637,0.0001681111,0.0001527578,0.0001596411,0.0001047973],"domain_scores_gemma":[0.9995152,0.000135133,0.00008414299,0.00018613,0.00004690843,0.00003253492],"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":[0.000002184728,0.00002025973,0.006863244,0.00000429709,0.00001256575,5.666316e-7,0.001115272,0.9788192,0.0001722769,0.007781702,0.00008096336,0.005127498],"study_design_scores_gemma":[0.00016414,0.00009678183,0.02388473,0.000009135845,0.00000333015,0.000002472849,0.0001581294,0.9739937,0.0007768098,0.0001459009,0.0007079458,0.00005692464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05878504,0.00002033414,0.9357699,0.0004235433,0.00003114629,0.00006111545,0.000001024657,0.00006903531,0.004838863],"genre_scores_gemma":[0.891873,0.00003969964,0.0971875,0.00006714182,0.00002097698,0.000001443122,0.00000398078,0.000003700029,0.01080254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8385824,"threshold_uncertainty_score":0.1932512,"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."}}