{"id":"W2963430540","doi":"10.1609/aaai.v33i01.33015789","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Ensemble learning; Search tree; Computer science; Perspective (graphical); Tree (set theory); Control (management); Artificial intelligence; Value (mathematics); Machine learning; Search algorithm; Ensemble forecasting; Mathematical optimization; Algorithm; Mathematics","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":[0.001308503,0.0009044402,0.00144231,0.0005936419,0.0004169865,0.0007043126,0.00135572,0.001289401,0.003222238],"category_scores_gemma":[0.002741476,0.0004574245,0.0006004969,0.0005409044,0.0006718455,0.001075179,0.001267669,0.001760626,0.0006703553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005468339,"about_ca_system_score_gemma":0.000998823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003830008,"about_ca_topic_score_gemma":0.003638696,"domain_scores_codex":[0.9995263,0.0001520579,0.0000238249,0.00009821248,0.0001419073,0.00005776704],"domain_scores_gemma":[0.9989931,0.0006457747,0.0000709913,0.00007511209,0.0001527686,0.00006223704],"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":[0.00007624582,0.00003499321,0.0003646703,0.00004287212,0.00005659261,0.00003714851,0.00004302588,0.9001227,0.0009593901,0.01231714,0.001445922,0.08449926],"study_design_scores_gemma":[0.000005287057,0.00001415586,0.00001823202,0.000003133126,0.00000288508,0.000005181844,0.000001716942,0.9976222,0.0001145529,0.001890556,0.0003198601,0.000002192943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003808954,0.0001809626,0.9943263,0.00006667293,0.00003391087,0.00002546321,0.00002074132,0.0003420248,0.001195072],"genre_scores_gemma":[0.474772,0.0003121614,0.5196019,0.0002777235,0.0001056344,0.0003652769,0.0002157375,0.0002628721,0.0040867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003830008,"threshold_uncertainty_score":0.01077944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04875294031259728,"score_gpt":0.2894369969026623,"score_spread":0.2406840565900651,"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."}}