{"id":"W2963800416","doi":"","title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematical proof; Markov decision process; Contraction (grammar); Property (philosophy); Computer science; Mathematics; Applied mathematics; Mathematical optimization; Measure (data warehouse); Class (philosophy); Markov process; Linear model; Artificial intelligence; Machine learning; Statistics","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":[0.001142309,0.000488501,0.0004210988,0.0004212109,0.0006062806,0.0002851833,0.001322302,0.0001858497,0.00005324014],"category_scores_gemma":[0.000841715,0.0003359763,0.0001595655,0.000343381,0.0002588,0.0007365947,0.000225782,0.0005869868,0.00009424819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000254692,"about_ca_system_score_gemma":0.000971865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006981543,"about_ca_topic_score_gemma":9.065002e-7,"domain_scores_codex":[0.9968311,0.0002727876,0.0004710183,0.0008239722,0.0006782445,0.0009228412],"domain_scores_gemma":[0.9971045,0.0008285419,0.0004532508,0.0009167666,0.0004344889,0.0002624787],"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":[0.0001882144,0.00001522198,0.00005302452,0.00001908062,0.00002695886,0.000001817935,0.0004753046,0.5985681,0.0004307534,0.3939979,0.00001575175,0.00620784],"study_design_scores_gemma":[0.001732922,0.001571581,0.00001634388,0.0003082883,0.00001817777,0.000002317413,0.00008121869,0.9720318,0.0009719233,0.0215121,0.001205578,0.0005477313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001689734,0.000007153967,0.9836047,0.001360416,0.0001097897,0.0005198233,0.000001538199,0.0007161811,0.01199061],"genre_scores_gemma":[0.9415168,0.00001674277,0.03160009,0.0004449525,0.00009973693,0.0001236095,0.00001570402,0.00007344195,0.02610897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9520047,"threshold_uncertainty_score":0.9999092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0519210604033747,"score_gpt":0.2934808180844667,"score_spread":0.2415597576810921,"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."}}