{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002755492,0.001290905,0.001251687,0.0006355734,0.0004160066,0.001429414,0.001248411,0.001365303,0.003735832],"category_scores_gemma":[0.00661817,0.000408592,0.0007462099,0.000792913,0.00221286,0.001911089,0.001512094,0.002708804,0.0007491905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001329369,"about_ca_system_score_gemma":0.001176127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00189009,"about_ca_topic_score_gemma":0.001125289,"domain_scores_codex":[0.9983274,0.0008559524,0.00008921891,0.0001947893,0.0004460027,0.00008648474],"domain_scores_gemma":[0.9970747,0.002184784,0.000211929,0.0001442213,0.0002838113,0.0001005619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008029347,0.000084321,0.0005894124,0.0004832615,0.0001143035,0.00008240181,0.0001818332,0.3325714,0.0009476939,0.5326953,0.004120656,0.1280491],"study_design_scores_gemma":[0.00007246387,0.0001119454,0.0001345749,0.0001085337,0.00002649171,0.0000584776,0.00002705085,0.6398276,0.000626015,0.3457177,0.0132643,0.00002475942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002021044,0.004838028,0.9833847,0.0006671561,0.000192279,0.00006211155,0.00003009302,0.0001453464,0.00865915],"genre_scores_gemma":[0.5322445,0.01285434,0.4339186,0.0009337204,0.001129511,0.001088159,0.0001580178,0.0002081303,0.01746494],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003735832,"threshold_uncertainty_score":0.01457262,"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."}}