{"id":"W4391306093","doi":"10.1109/rose60297.2023.10410776","title":"An Online Model-Free Reinforcement Learning Approach for 6-DOF Robot Manipulators","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Control theory (sociology); Robot; Adaptive control; MATLAB; Robot manipulator; Tracking error; Kernel (algebra); Degrees of freedom (physics and chemistry); Control (management); Control engineering; Artificial intelligence; Mathematics; Engineering","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":[0.0004772543,0.0001799583,0.0001944577,0.0001648147,0.0001867756,0.0001385949,0.001545793,0.00006644311,0.000002547841],"category_scores_gemma":[0.0000734005,0.0001631448,0.00009728268,0.0004192421,0.00002847546,0.0004837101,0.0004663638,0.0001513376,0.00001260206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007198062,"about_ca_system_score_gemma":0.00005635354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003110999,"about_ca_topic_score_gemma":0.00001098155,"domain_scores_codex":[0.9983414,0.00003431426,0.0002670039,0.0005274509,0.0003179531,0.0005119091],"domain_scores_gemma":[0.9987189,0.00005285552,0.00008735492,0.0009068017,0.00009977805,0.0001343656],"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":[0.000007127779,0.00004611252,0.00007059274,0.000009984324,0.0000187114,0.000001410584,0.0001705423,0.8693861,0.0002001298,0.1139503,0.0002134949,0.01592554],"study_design_scores_gemma":[0.0006617135,0.0002214607,0.0001474036,0.000003521725,0.000007671813,0.000001746307,0.00007596333,0.9953902,0.00003562587,0.002960365,0.0002815864,0.0002127395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001655775,0.000007275781,0.995248,0.0003258767,0.00008169769,0.0005393923,0.000002016907,0.001268754,0.0008712533],"genre_scores_gemma":[0.5450416,0.000001345516,0.4515886,0.0001441847,0.00004475126,0.00008291298,0.00008061957,0.0000178245,0.002998215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5436593,"threshold_uncertainty_score":0.6652851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05925569399817362,"score_gpt":0.2849001201848312,"score_spread":0.2256444261866576,"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."}}