{"id":"W4388741154","doi":"10.1016/j.engappai.2023.107518","title":"Reinforcement learning to achieve real-time control of triple inverted pendulum","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Inverted pendulum; Markov decision process; Process (computing); Convergence (economics); Sample (material); Artificial intelligence; Machine learning; Markov process","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":[0.0005185108,0.0001488232,0.0002483322,0.0004289867,0.00008130835,0.00003806972,0.0009103658,0.0000600626,0.00002726485],"category_scores_gemma":[0.0002703928,0.0001701062,0.00007718653,0.001903095,0.00003794937,0.0001443387,0.0002007195,0.0001649174,0.0004448163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004478463,"about_ca_system_score_gemma":0.00004924119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005954454,"about_ca_topic_score_gemma":7.065594e-7,"domain_scores_codex":[0.9983416,0.00002586033,0.0006874096,0.0002854051,0.0003596652,0.0003000775],"domain_scores_gemma":[0.998629,0.0002291916,0.0002037374,0.0006339292,0.0001971912,0.0001069015],"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":[0.000007316722,0.00001397394,0.00001450492,0.00002707255,0.00001980873,3.886494e-7,0.0004996159,0.9021786,0.04348249,0.0432143,0.0000647976,0.01047716],"study_design_scores_gemma":[0.00002950368,0.0001753429,0.00006364934,0.00003028563,0.000007565319,5.627057e-7,0.00006739946,0.954044,0.04421671,0.0002881996,0.0009333189,0.0001434056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002082914,0.000006787484,0.9962185,0.000222101,0.0001128108,0.0005522197,0.000001773954,0.0003908748,0.000412033],"genre_scores_gemma":[0.9699894,0.00002974187,0.02920509,0.00001522626,0.00003885068,0.000156976,0.00001269314,0.00001908825,0.0005329152],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9679065,"threshold_uncertainty_score":0.6936728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01839544774908922,"score_gpt":0.2608942312425003,"score_spread":0.2424987834934111,"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."}}