{"id":"W3191305580","doi":"10.1109/isscs52333.2021.9497411","title":"Inverted Pendulum Control with a Robotic Arm using Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Inverted pendulum; Reinforcement learning; Pendulum; Computer science; Benchmark (surveying); Double inverted pendulum; Robot; Control theory (sociology); Position (finance); Inertial measurement unit; Artificial intelligence; Simulation; Control (management); Engineering; Physics; Mechanical engineering; Nonlinear system; Geology","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":[0.0002566584,0.0002515384,0.0003090362,0.0001227616,0.0002916463,0.0004079474,0.0005724616,0.00007559857,0.000342632],"category_scores_gemma":[0.0001394141,0.0002172678,0.00007887823,0.0006760742,0.00005454158,0.0006098441,0.0003017164,0.0003849363,0.0001029725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001502607,"about_ca_system_score_gemma":0.0002693021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005978081,"about_ca_topic_score_gemma":0.00001813805,"domain_scores_codex":[0.9977461,0.0001448152,0.000392432,0.0004994956,0.000640898,0.0005762737],"domain_scores_gemma":[0.9985329,0.000122263,0.0001998952,0.0006735926,0.0002960112,0.0001753714],"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":[0.000007967031,0.00002252902,0.0017088,0.00001751369,0.00008075013,0.0001095608,0.0002761715,0.9848679,0.000724778,0.01157982,0.00003101303,0.0005732122],"study_design_scores_gemma":[0.001302878,0.0002520313,0.0002024808,0.00005202059,0.00003881467,0.0001203493,0.0001656319,0.9957253,0.001202608,0.00004264094,0.0005730454,0.0003221545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00112122,0.00004730998,0.9863355,0.0003595077,0.0002177595,0.0002041563,2.150846e-8,0.0003154948,0.01139899],"genre_scores_gemma":[0.8960489,0.000008558586,0.09798285,0.001066045,0.00004275572,0.000007869063,0.000005822529,0.00002315822,0.004814018],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8949277,"threshold_uncertainty_score":0.8859925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01975879567519837,"score_gpt":0.2358191611717154,"score_spread":0.2160603654965171,"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."}}