{"id":"W7124165107","doi":"10.65109/twxw5772","title":"Sigma point policy iteration","year":2008,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Iterated function; Sigma; Function (biology); Fixed point; Point (geometry); Order (exchange); Markov decision process; Bellman equation","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":[0.00118578,0.0008170186,0.001333853,0.0004694215,0.0004256741,0.0009118154,0.0009307664,0.001239053,0.004990209],"category_scores_gemma":[0.004385088,0.0005301931,0.0006172553,0.0004846268,0.001094539,0.0008433717,0.001423196,0.00134812,0.00112136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008022429,"about_ca_system_score_gemma":0.001496238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003052514,"about_ca_topic_score_gemma":0.002302959,"domain_scores_codex":[0.9994704,0.0001729768,0.00003501484,0.00009422028,0.0001651953,0.00006218648],"domain_scores_gemma":[0.998442,0.001012106,0.00009982313,0.0001110672,0.0002769451,0.00005807221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000159808,0.00008855011,0.000907106,0.0001679351,0.00006067259,0.00007648698,0.0001656547,0.7700327,0.002622918,0.05111386,0.002174982,0.1724292],"study_design_scores_gemma":[0.00001359242,0.00003365334,0.00003172514,0.00001113299,0.00000404147,0.000013911,0.000008219773,0.989594,0.0007445714,0.008758645,0.0007814543,0.000005001016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005887225,0.0001314874,0.9912964,0.00007601561,0.00003962163,0.00005196347,0.00001628641,0.0003261259,0.002174837],"genre_scores_gemma":[0.4459912,0.0002915887,0.54394,0.000284304,0.00005590585,0.000614039,0.0001884447,0.0002484921,0.008386105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004990209,"threshold_uncertainty_score":0.01669395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02866147398799097,"score_gpt":0.2603251415755973,"score_spread":0.2316636675876063,"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."}}