{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006413198,0.0006318289,0.0004265347,0.0002080171,0.0002927369,0.0004074313,0.0006303354,0.000619761,0.001466796],"category_scores_gemma":[0.001307107,0.0002350587,0.0003006207,0.000132563,0.0005917566,0.0003507623,0.0006140434,0.0008495569,0.0001811493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005994173,"about_ca_system_score_gemma":0.0007931734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005458185,"about_ca_topic_score_gemma":0.004244899,"domain_scores_codex":[0.9998271,0.00003897102,0.000009388291,0.00003458784,0.00005297653,0.0000370772],"domain_scores_gemma":[0.999566,0.0001781759,0.00006527764,0.00003728286,0.0001126953,0.00004053092],"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":[0.0001026789,0.0000951654,0.0006632642,0.00005249251,0.00002797287,0.00009694738,0.0000493834,0.9427521,0.006805792,0.003584417,0.0006041373,0.04516561],"study_design_scores_gemma":[0.000008650456,0.00005560492,0.00006328771,0.000002717803,0.000002535233,0.000005345023,0.000002194614,0.9983368,0.0006626321,0.0006689656,0.0001888193,0.000002365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09725551,0.0002411483,0.8952125,0.0002582539,0.00009500285,0.0001011186,0.00003086215,0.0008933519,0.005912364],"genre_scores_gemma":[0.9513046,0.00004870878,0.04670352,0.00006498639,0.00001253718,0.00007436146,0.00002590503,0.00002051368,0.001744847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005458185,"threshold_uncertainty_score":0.01085281,"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."}}