{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006857785,0.0002792653,0.0003939899,0.0001282662,0.000182788,0.0004439681,0.002486062,0.0001122583,0.0000463225],"category_scores_gemma":[0.0001475287,0.0001945699,0.0001128488,0.0004453006,0.0002082347,0.000698142,0.000211863,0.0003434756,0.0001035901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005500747,"about_ca_system_score_gemma":0.0001680744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002218712,"about_ca_topic_score_gemma":0.0000051949,"domain_scores_codex":[0.9976074,0.00002523688,0.0004763553,0.0006171835,0.0007178301,0.0005559811],"domain_scores_gemma":[0.9975915,0.000210815,0.0003756566,0.0005044559,0.001183093,0.0001344679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003123283,0.0002161804,0.0009389436,0.00008843421,0.00007446129,8.213211e-7,0.002243118,0.01088307,0.06846494,0.5930616,0.0001097564,0.3236063],"study_design_scores_gemma":[0.0001593472,0.001589921,0.0001145404,0.0001247781,0.0000156546,0.000004652789,0.0005415235,0.7491407,0.2434085,0.004493042,0.0001564359,0.0002508112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0642767,0.000005809146,0.9277467,0.001220174,0.0003583681,0.00142461,0.000005737993,0.0001234392,0.004838426],"genre_scores_gemma":[0.9608443,0.000005907327,0.03734424,0.000215059,0.00007306519,0.00004862729,0.000001072909,0.00002445065,0.001443312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8965676,"threshold_uncertainty_score":0.793433,"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."}}