{"id":"W4388191662","doi":"10.1016/j.asoc.2023.110975","title":"Ensemble reinforcement learning: A survey","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Science and Technology Innovation Group of Shanxi Province; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Popularity; Generalization; Field (mathematics); Ensemble learning; Artificial intelligence; Machine learning; Open research; Selection (genetic algorithm); Data science","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001897115,0.0002481542,0.0002698866,0.0002373892,0.0005180044,0.0003192042,0.001125598,0.00009335207,0.00001779605],"category_scores_gemma":[0.0002607606,0.0002655759,0.00007129212,0.001529371,0.00004766952,0.000151799,0.001199054,0.0004373861,0.001734178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007569789,"about_ca_system_score_gemma":0.00008675491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004250084,"about_ca_topic_score_gemma":0.000003078113,"domain_scores_codex":[0.9974181,0.0001090369,0.0004776124,0.0005644055,0.0006407648,0.0007900738],"domain_scores_gemma":[0.998013,0.0008615177,0.0002421489,0.0006475452,0.00009679159,0.0001389937],"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":[0.000003770723,0.000005998801,0.001776562,0.00001584367,0.00002255494,0.000008424397,0.0009975538,0.9639947,0.0004003336,0.0175137,0.001179397,0.01408119],"study_design_scores_gemma":[0.000341124,0.00005958553,0.008140815,0.00001656651,0.000003512279,0.000003696325,0.00006727902,0.9863053,0.0003814666,0.0002800034,0.004084138,0.0003165381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01381373,0.000006925399,0.9646641,0.0001052415,0.0003915356,0.0002606582,1.075776e-7,0.001925114,0.01883258],"genre_scores_gemma":[0.9833896,0.000005195251,0.01413075,0.0002982714,0.00007735335,0.00001009498,0.00004512463,0.00003167538,0.002011942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9695759,"threshold_uncertainty_score":0.9999796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03247530673738754,"score_gpt":0.2652782368121937,"score_spread":0.2328029300748062,"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."}}