{"id":"W4230558268","doi":"10.1007/978-1-4899-7502-7_109-1","title":"Gaussian Process Reinforcement Learning","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Process (computing); Gaussian process; Computer science; Artificial intelligence; Gaussian; Machine learning; Physics","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":[0.0005479961,0.0007649238,0.0008763583,0.0003648011,0.0002802967,0.001345659,0.001028352,0.001057048,0.01679357],"category_scores_gemma":[0.002172852,0.0002796273,0.0003641111,0.0007112856,0.0007669667,0.0008733452,0.0009133997,0.001595828,0.004750254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007224762,"about_ca_system_score_gemma":0.0008740582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001862737,"about_ca_topic_score_gemma":0.002683198,"domain_scores_codex":[0.9997411,0.00007208724,0.00001020021,0.0000641556,0.00009180037,0.00002055317],"domain_scores_gemma":[0.9995455,0.0002517642,0.00002571171,0.00005976247,0.00008791596,0.00002924715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006385325,0.0001282436,0.0004836604,0.0002275218,0.00006608758,0.00008264636,0.00007814122,0.1684417,0.001604067,0.3407079,0.04777882,0.4403374],"study_design_scores_gemma":[0.00002673291,0.00005726319,0.0003497364,0.00009456261,0.00002506078,0.0001153239,0.00001792281,0.584456,0.001102157,0.3566315,0.05709218,0.00003149796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003000325,0.00689579,0.9157613,0.001036462,0.0004401018,0.0000471406,0.0001904025,0.0009976226,0.07163079],"genre_scores_gemma":[0.4063084,0.01439018,0.3829026,0.001184689,0.0007733925,0.0003910146,0.001090847,0.000620038,0.1923388],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01679357,"threshold_uncertainty_score":0.05618012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01665900846311922,"score_gpt":0.2669173883033986,"score_spread":0.2502583798402794,"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."}}