{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008443494,0.0005511279,0.000724925,0.0002926843,0.0003419565,0.0002101272,0.001991072,0.0003913943,0.0001818282],"category_scores_gemma":[0.0004262616,0.0005058374,0.00007007518,0.0001081841,0.0001305625,0.000522275,0.001781895,0.001667864,0.0000387459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001824951,"about_ca_system_score_gemma":0.0002021519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003245042,"about_ca_topic_score_gemma":0.00001101533,"domain_scores_codex":[0.996934,0.00006545179,0.0007581635,0.001201351,0.0005958533,0.000445185],"domain_scores_gemma":[0.9973563,0.0002639772,0.0009721112,0.001079183,0.000112668,0.0002157367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003839004,0.00002731075,0.004722499,0.001799935,0.0001989555,0.00008364778,0.003293014,0.001283578,0.000006290005,0.1366357,0.001785278,0.8501254],"study_design_scores_gemma":[0.000526758,0.0005373298,0.0001001751,0.001329852,0.0001048255,0.00007659037,0.00007679483,0.1542752,0.000006688771,0.002678237,0.8392683,0.001019324],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00005491882,0.001871211,0.2435435,0.0003316923,0.0002266526,0.0001735657,0.0000161939,0.0002372556,0.753545],"genre_scores_gemma":[0.1570066,0.01012175,0.05491553,0.0002441974,0.0007887313,0.0000197879,0.001482012,0.0002097129,0.7752116],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8491061,"threshold_uncertainty_score":0.9997393,"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."}}