{"id":"W2137486584","doi":"10.5555/1402383.1402439","title":"Sigma point policy iteration","year":2008,"lang":"en","type":"article","venue":"","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Iterated function; Sigma; Bellman equation; Fixed point; Mathematical optimization; Temporal difference learning; Artificial intelligence; Algorithm; Applied mathematics; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00001253711,0.00004497801,0.00004254585,0.00002534315,0.0000817507,0.00001040978,0.00002702561,0.000009987382,0.001874727],"category_scores_gemma":[5.754492e-7,0.00003661091,0.00003576961,0.00006941064,0.00001292123,0.00008679108,0.000008909763,0.00004262839,0.00008533665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005222565,"about_ca_system_score_gemma":0.00001798866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001453438,"about_ca_topic_score_gemma":4.470495e-7,"domain_scores_codex":[0.9997176,0.000008497766,0.00006831804,0.00007703855,0.00004484621,0.00008371365],"domain_scores_gemma":[0.9998518,0.000004942356,0.00001526052,0.0000731261,0.00001478462,0.00004013992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002309021,0.0002136072,0.0103506,0.00000278229,0.00003998154,0.000003152011,0.0007803292,0.006100664,0.005071906,0.7342703,0.1464841,0.09665945],"study_design_scores_gemma":[0.003979093,0.0003283473,0.0224875,0.00003538839,0.00003241377,0.0001074292,0.0007039498,0.3164987,0.1036065,0.09537739,0.454986,0.001857323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3790886,0.000009792456,0.1874521,0.002915487,0.0001888875,0.0001113904,0.000002456266,0.00007946173,0.4301518],"genre_scores_gemma":[0.9837835,0.000001919588,0.000261188,0.0002927009,0.0008429346,0.00000451392,0.00001035417,0.000004118007,0.01479876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6388929,"threshold_uncertainty_score":0.9990377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0175388229952415,"score_gpt":0.2482758482641924,"score_spread":0.2307370252689509,"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."}}