{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002415697,0.00122857,0.00313331,0.001390213,0.0004176577,0.001844514,0.002028817,0.001290101,0.002254658],"category_scores_gemma":[0.004055099,0.0006714781,0.0009979479,0.003551329,0.0007605173,0.002308961,0.001623261,0.001686856,0.0008028322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007073669,"about_ca_system_score_gemma":0.001139282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002578477,"about_ca_topic_score_gemma":0.002215151,"domain_scores_codex":[0.9988179,0.0003147068,0.0001210652,0.0003024316,0.0003819614,0.00006187928],"domain_scores_gemma":[0.997372,0.001719424,0.00009181019,0.0002316249,0.0005101206,0.00007510272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006595691,0.0002562566,0.001757255,0.001225896,0.0002151256,0.0000306115,0.00007066156,0.09399552,0.0006608848,0.025306,0.005551958,0.8708639],"study_design_scores_gemma":[0.00004285538,0.0003999245,0.002162552,0.0005961474,0.0002000599,0.0002935529,0.0001187224,0.853248,0.002162318,0.08041847,0.06027726,0.00008004483],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01099957,0.2791015,0.6936128,0.00125657,0.0006091995,0.0001228439,0.0001495036,0.0004835982,0.01366454],"genre_scores_gemma":[0.3503654,0.3429073,0.2902891,0.0009503708,0.00312845,0.0004454179,0.0007946542,0.0003378477,0.01078143],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.00313331,"threshold_uncertainty_score":0.0127756,"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."}}