{"id":"W3196801835","doi":"10.48550/arxiv.2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Machine learning; Error-driven learning; Component (thermodynamics); Psychology; Social 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001771189,0.0002542621,0.0004511429,0.0004275293,0.00006537855,0.0001178813,0.001268988,0.0002485692,0.00003134581],"category_scores_gemma":[0.0004888544,0.0003256301,0.0001103614,0.001229732,0.00005952263,0.0006423161,0.002407808,0.0008384475,0.000009720517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002581415,"about_ca_system_score_gemma":0.0003485068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001112669,"about_ca_topic_score_gemma":0.0001450098,"domain_scores_codex":[0.9970815,0.001228338,0.0004606337,0.0007786827,0.0001509972,0.0002999187],"domain_scores_gemma":[0.9975648,0.0003720613,0.0005935967,0.001025691,0.0003631738,0.00008067879],"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":[0.00001055006,0.00002250062,0.0102319,0.00007781747,0.00004357419,0.00005151586,0.0007504982,0.9817227,0.00007707986,0.006370243,0.000007546066,0.000634084],"study_design_scores_gemma":[0.0003086258,0.00007777757,0.00915333,0.0001580335,0.00001637703,5.398186e-7,0.0001575907,0.989032,0.0004323317,0.0003411409,0.00003937295,0.000282923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02433543,0.00004601302,0.9733979,0.00001797426,0.0003810409,0.0002272307,4.366104e-7,0.00008625224,0.00150775],"genre_scores_gemma":[0.9680552,0.0002314637,0.03035881,0.00001876604,0.00001030565,0.000001163467,0.00006536915,0.00001435834,0.001244575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9437197,"threshold_uncertainty_score":0.9999196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1871962960421404,"score_gpt":0.2701565752149955,"score_spread":0.08296027917285512,"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."}}