{"id":"W2100785108","doi":"10.7551/mitpress/7503.003.0062","title":"Bayesian Policy Gradient Algorithms","year":2007,"lang":"en","type":"book-chapter","venue":"The MIT Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Bayesian probability; Computer science; Algorithm; Artificial intelligence","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":[0.0004977568,0.0005007695,0.0003743336,0.0002464243,0.0002644268,0.000313839,0.003059204,0.0003148695,0.00002170007],"category_scores_gemma":[0.00002422421,0.0003748428,0.0002445533,0.00001955679,0.0002535039,0.00008483228,0.001128568,0.0008554027,0.0001368965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001605906,"about_ca_system_score_gemma":0.0001424228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000187874,"about_ca_topic_score_gemma":0.000007284363,"domain_scores_codex":[0.9974422,0.00004420739,0.0005094109,0.0005683975,0.0008086952,0.0006271177],"domain_scores_gemma":[0.9970571,0.0001689199,0.0003982395,0.002086051,0.0001079832,0.0001816704],"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":[0.00000395036,0.000003215642,1.961143e-7,0.00002331622,0.0001146643,0.00004273781,0.0008429682,0.005700462,0.000002843327,0.9351643,0.001413759,0.05668754],"study_design_scores_gemma":[0.00021361,0.0001036605,0.000003059567,0.0001387195,0.00005927646,0.00004988634,0.000002098067,0.05454915,0.0001732644,0.01837923,0.9257846,0.0005434372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[9.136226e-8,0.0001769739,0.4581589,0.0001019294,0.0003612801,0.0002901351,0.000002351919,0.0001835712,0.5407248],"genre_scores_gemma":[0.0003320213,0.00005062473,0.009191939,0.0007925344,0.0008218131,0.00001491375,0.000005995618,0.00008095475,0.9887092],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9243708,"threshold_uncertainty_score":0.9998704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05302789778127596,"score_gpt":0.2785326680918616,"score_spread":0.2255047703105856,"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."}}