{"id":"W4379881949","doi":"10.1007/s13369-023-07934-2","title":"Reinforcement Learning DDPG–PPO Agent-Based Control System for Rotary Inverted Pendulum","year":2023,"lang":"en","type":"article","venue":"Arabian Journal for Science and Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Inverted pendulum; Control theory (sociology); PID controller; Reinforcement learning; Benchmark (surveying); Controller (irrigation); Linear-quadratic regulator; Pendulum; Computer science; Nonlinear system; Control engineering; Engineering; Artificial intelligence; Control (management); Physics; Temperature control","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":[0.002543387,0.0001835275,0.000217111,0.0005397739,0.0009816148,0.0006603834,0.0008235101,0.0000470204,0.000001362268],"category_scores_gemma":[0.0005831941,0.0001720982,0.000101236,0.0009129234,0.00006764613,0.0009390915,0.00007831935,0.0002461371,0.00001081456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001974944,"about_ca_system_score_gemma":0.0002234906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003128965,"about_ca_topic_score_gemma":2.935935e-7,"domain_scores_codex":[0.9979051,0.00001731298,0.0003962197,0.000327519,0.0005917904,0.0007620005],"domain_scores_gemma":[0.9987774,0.0002139698,0.0001625955,0.0002361361,0.0003033422,0.0003065906],"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":[0.000008173041,0.000002009434,0.0001984591,0.0001045354,0.00001637462,0.000008771764,0.0001922446,0.9905953,0.003996832,0.00260337,0.0002327246,0.002041193],"study_design_scores_gemma":[0.001117206,0.0003092505,0.0004326342,0.0001537342,0.00001388256,0.00004504939,0.0001464768,0.9924547,0.0009899378,0.00001953186,0.004101843,0.0002157688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008772662,0.00003342766,0.9883223,0.0005532353,0.001508993,0.0004304625,8.316032e-7,0.0002989612,0.00007911285],"genre_scores_gemma":[0.9859663,0.0000113301,0.01346166,0.0001411936,0.0001269179,0.00005602789,0.000002929666,0.00001934437,0.0002143528],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9771936,"threshold_uncertainty_score":0.7549887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01910297911865512,"score_gpt":0.2391209986723254,"score_spread":0.2200180195536703,"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."}}