{"id":"W64134055","doi":"","title":"Bayesian Learning of Recursively Factored Environments","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Factoring; Computer science; Reinforcement learning; Factorization; Inference; Class (philosophy); Artificial intelligence; Bayesian probability; Task (project management); Machine learning; Scaling; Bayesian inference; Theoretical computer science; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.00008425806,0.00009130381,0.0001117025,0.00006313683,0.00005188117,0.00005920289,0.0005508716,0.00004287671,0.0004278636],"category_scores_gemma":[0.00005432594,0.0000802276,0.00004106392,0.0001182832,0.00003760568,0.0004598006,0.0001970948,0.0001270991,0.0004260575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002566856,"about_ca_system_score_gemma":0.00001298874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004484742,"about_ca_topic_score_gemma":1.299615e-7,"domain_scores_codex":[0.9990883,0.00004623947,0.000205914,0.0001849271,0.0002696615,0.0002049607],"domain_scores_gemma":[0.999413,0.00005823049,0.0001289065,0.000310382,0.00002030016,0.0000691567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003127486,0.00007761744,0.05572015,0.00002889377,0.00008704161,0.00000425954,0.002536405,0.8177065,0.02661071,0.05191677,0.002425615,0.04288286],"study_design_scores_gemma":[0.0002686048,0.0002128591,0.03439582,0.00001574143,0.000003662691,0.000002164232,0.0001032807,0.9478611,0.01077154,0.0005426625,0.005611896,0.0002106857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005116636,0.000006440732,0.9753566,0.000187101,0.00008675558,0.0001250158,4.843842e-8,0.00006422593,0.01905712],"genre_scores_gemma":[0.9349412,0.000007367906,0.05641385,0.00007176708,0.000009199557,0.000004972843,0.000001302489,0.000006562921,0.00854377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9298246,"threshold_uncertainty_score":0.5476249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00994807483159242,"score_gpt":0.2088798920242947,"score_spread":0.1989318171927023,"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."}}