{"id":"W4312372616","doi":"10.1109/aeeca55500.2022.9918998","title":"Exploration Methods in Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Strengths and weaknesses; Error-driven learning; Focus (optics); Artificial intelligence; Human–computer interaction; Engineering; Psychology","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":[0.0004389834,0.0001653247,0.0001722883,0.0005678769,0.0001238883,0.0001144397,0.000751718,0.00003523847,0.00003073255],"category_scores_gemma":[0.00002872135,0.0001940985,0.00003000906,0.0008879555,0.00001674267,0.0004885536,0.0002566541,0.0007191596,0.000006669783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003113099,"about_ca_system_score_gemma":0.00004148161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006501257,"about_ca_topic_score_gemma":0.000001185917,"domain_scores_codex":[0.9983606,0.000106349,0.0003967342,0.0004513896,0.0004218008,0.0002630975],"domain_scores_gemma":[0.9993202,0.0002165727,0.0001166139,0.0002368246,0.00005315332,0.00005660169],"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":[0.000005981377,0.00003021779,0.00006713848,0.000004205749,0.000004833652,0.000002458793,0.000106212,0.7328575,0.0002991412,0.1955906,0.0000107791,0.07102092],"study_design_scores_gemma":[0.0003092221,0.0002075068,0.0001226216,0.00001407944,0.000001316981,0.000008343967,0.00001904599,0.9725972,0.0001507921,0.001649674,0.02472813,0.0001920095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002175858,0.000141289,0.9967522,0.0004024691,0.0003629881,0.000270448,5.415504e-7,0.0001228148,0.00172968],"genre_scores_gemma":[0.8304901,0.0009208639,0.1660184,0.000273373,0.0001339188,0.001559376,0.00003703342,0.00002310536,0.0005438155],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8307338,"threshold_uncertainty_score":0.7915109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02631831350883449,"score_gpt":0.326034692121068,"score_spread":0.2997163786122335,"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."}}