{"id":"W2964760189","doi":"","title":"Epsilon-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Bayesian probability; Computer science; Perspective (graphical); Mathematical optimization; Monotone polygon; Convergence (economics); Greedy algorithm; Simulated annealing; Bellman equation; Q-learning; Function (biology); Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003238508,0.0002881435,0.0002933266,0.0003219415,0.000203862,0.0001548969,0.001768733,0.000118955,0.00001238015],"category_scores_gemma":[0.0002006936,0.0003489728,0.0001067158,0.001749237,0.00004150367,0.001502813,0.0009990104,0.0004400138,0.0001717681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00024331,"about_ca_system_score_gemma":0.0001342977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004944449,"about_ca_topic_score_gemma":0.00001497224,"domain_scores_codex":[0.9978074,0.000140188,0.0003444177,0.0009138107,0.0002454466,0.0005487538],"domain_scores_gemma":[0.9984164,0.00007232503,0.0001813847,0.0008692304,0.0001000773,0.00036056],"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":[0.00004877622,0.00003004856,0.001877536,0.00003165285,0.00001334561,0.00002827952,0.002268971,0.893671,0.0001007075,0.1016162,0.0002394097,0.00007404562],"study_design_scores_gemma":[0.000915941,0.000264916,0.0001099038,0.00002740028,0.00001342478,0.000001490774,0.0003703749,0.996316,0.0001118371,0.001279187,0.0002059383,0.0003835948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008175722,0.000005416678,0.9745935,0.0004354863,0.00007120399,0.000450777,3.577142e-7,0.0002924862,0.01597505],"genre_scores_gemma":[0.9312975,0.00001413725,0.06633697,0.0005027197,0.00002234581,0.000003493189,0.000009670644,0.00002310754,0.001790036],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9231218,"threshold_uncertainty_score":0.9998962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1159792376073298,"score_gpt":0.1931123848080355,"score_spread":0.07713314720070566,"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."}}