{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003757003,0.0005644786,0.0007410191,0.0002146494,0.0005871545,0.0006414977,0.001023683,0.0008073486,0.002920131],"category_scores_gemma":[0.0006754671,0.0002567676,0.0002766177,0.0001621924,0.0004028468,0.0003355782,0.0008965053,0.0005357775,0.0005334284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003229506,"about_ca_system_score_gemma":0.0007010905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004682449,"about_ca_topic_score_gemma":0.003698131,"domain_scores_codex":[0.9997881,0.00003616526,0.00001374457,0.00006366989,0.0000625801,0.00003583396],"domain_scores_gemma":[0.9997774,0.0000464383,0.00003328101,0.00001804972,0.0001004611,0.00002444383],"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":[0.0004896323,0.0002181717,0.001628586,0.0003462992,0.00008694431,0.0005679633,0.0001544938,0.7866663,0.02720603,0.006200247,0.003738081,0.1726973],"study_design_scores_gemma":[0.00004415106,0.0001676083,0.0003034922,0.00001015887,0.000014432,0.00005361924,0.000008881433,0.9955225,0.002047505,0.0005912601,0.001228111,0.000008349662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0915784,0.0008382311,0.8807762,0.0005824195,0.0005325236,0.0002505845,0.00008921975,0.001817205,0.02353531],"genre_scores_gemma":[0.9703346,0.0001322305,0.02460447,0.00009903751,0.00004175582,0.0001494813,0.00003939079,0.00001825942,0.004580765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004682449,"threshold_uncertainty_score":0.009768784,"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."}}