{"id":"W2951621135","doi":"10.2316/j.2019.201-2931","title":"MODEL-FREE ONLINE REINFORCEMENT LEARNING OF A ROBOTIC MANIPULATOR","year":2019,"lang":"en","type":"article","venue":"Mechatronic systems and control","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Torque; Reinforcement learning; Joint (building); Robot manipulator; Manipulator (device); Computer science; Control theory (sociology); Artificial intelligence; Control engineering; Robot; Simulation; Engineering; Control (management); Structural engineering; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001754877,0.0001870336,0.0004874128,0.00008657118,0.00003042863,0.00002295165,0.0001393366,0.00009291731,0.00001021584],"category_scores_gemma":[0.00001791824,0.0001769868,0.00006231973,0.00007167776,0.000008789242,0.0001495027,0.00002696383,0.0001342699,0.000008544324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001019902,"about_ca_system_score_gemma":0.00001981804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004486472,"about_ca_topic_score_gemma":0.000008217025,"domain_scores_codex":[0.9988236,0.0000329567,0.0004732536,0.0001848036,0.0002039911,0.0002813939],"domain_scores_gemma":[0.9993464,0.00003722919,0.0001329963,0.000360753,0.00005922287,0.00006343002],"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":[0.00001724069,0.000005691403,0.0002912554,0.0002565376,0.00009050922,5.423267e-7,0.0000507348,0.9831873,0.005101339,0.01071975,0.00000840973,0.0002707052],"study_design_scores_gemma":[0.002724234,0.0000948401,0.0000393095,0.0001320204,0.00004587016,0.000006926334,0.000157842,0.996343,0.00003582988,0.00009845327,0.000152906,0.0001687547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0305939,0.004937155,0.9624111,0.00001719217,0.0004074198,0.0009000336,0.000006105906,0.0001865434,0.0005405557],"genre_scores_gemma":[0.9985943,0.00005959209,0.0003532016,0.000008905811,0.00007124472,0.00005549332,0.00000925403,0.00004440547,0.0008035506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9680005,"threshold_uncertainty_score":0.7217314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006969709640097293,"score_gpt":0.1888515896554948,"score_spread":0.1818818800153975,"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."}}