{"id":"W7124253663","doi":"10.65109/rjqi2619","title":"Off-Policy Evolutionary Reinforcement Learning with Maximum Mutations","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Scalability; Hyperparameter; Learning classifier system; Population; Evolutionary algorithm; Evolutionary computation; Sensitivity (control systems)","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":[0.001331056,0.0009923007,0.001182917,0.0005413817,0.0003691558,0.0007746307,0.001373549,0.001086833,0.003171808],"category_scores_gemma":[0.005718024,0.0004538115,0.000460232,0.000395937,0.001160125,0.0007732917,0.001410538,0.001245343,0.0006015392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007804705,"about_ca_system_score_gemma":0.0009889548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002055782,"about_ca_topic_score_gemma":0.00228106,"domain_scores_codex":[0.9993929,0.00021949,0.00002664924,0.0001021151,0.0001734766,0.00008539002],"domain_scores_gemma":[0.9979925,0.001314259,0.0001739019,0.0001883988,0.0002095179,0.0001213998],"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":[0.00008768242,0.00005984082,0.0005792799,0.00004460061,0.00003792095,0.00009873388,0.00005128097,0.9392878,0.001555106,0.01351163,0.0009577782,0.04372836],"study_design_scores_gemma":[0.00001544756,0.00001960805,0.00004106667,0.000005418503,0.000003927059,0.00001066855,0.00000342042,0.9955075,0.0002548977,0.003853096,0.0002816525,0.00000336498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03855835,0.0003413239,0.9528678,0.0002878654,0.0000926114,0.00009305566,0.00003784041,0.0008381098,0.006882971],"genre_scores_gemma":[0.8845026,0.0001428285,0.1091742,0.0002496897,0.00004242113,0.0002341611,0.00007242565,0.000139259,0.005442425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003171808,"threshold_uncertainty_score":0.01061076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507967767866917,"score_gpt":0.2466790227555951,"score_spread":0.231599345076926,"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."}}