{"id":"W2891236810","doi":"","title":"Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Artificial intelligence; Machine learning; Bayesian probability; Bellman equation; Domain (mathematical analysis); Function (biology); Mathematical optimization; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003885574,0.0002440458,0.0002111216,0.0002666189,0.0006520991,0.00140947,0.0006064018,0.00009715617,0.000001806324],"category_scores_gemma":[0.00008123305,0.0001985879,0.00003474632,0.0005553014,0.00008666357,0.007058052,0.0001330784,0.0002183858,0.00003497749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001438909,"about_ca_system_score_gemma":0.0001217527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002604243,"about_ca_topic_score_gemma":5.556727e-7,"domain_scores_codex":[0.9978254,0.00006306753,0.0006654976,0.0002438868,0.000803831,0.0003982598],"domain_scores_gemma":[0.9982294,0.00003100316,0.0006446411,0.0003752365,0.0006105974,0.0001090985],"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":[0.00001391648,0.0000111133,0.0003376985,0.0001651923,0.00000790629,3.172682e-7,0.007530181,0.985354,0.0000442026,0.002602434,0.0002601412,0.00367289],"study_design_scores_gemma":[0.0007354796,0.0003035837,0.00002960982,0.0001140209,0.000005391278,0.00003586079,0.0006888896,0.9958278,0.000189875,0.000009552587,0.001790171,0.000269797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001514539,0.00002027108,0.9837318,0.00009694678,0.0002191805,0.0005020763,2.077837e-7,0.0005929423,0.01332203],"genre_scores_gemma":[0.9780061,0.000001667494,0.02068715,0.0002746753,0.00007158335,0.0000978226,0.00004310816,0.00001508414,0.0008028018],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9764916,"threshold_uncertainty_score":0.9996272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01966117805250088,"score_gpt":0.2382829261831284,"score_spread":0.2186217481306275,"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."}}