{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006758026,0.0005982772,0.0006422844,0.0001997352,0.0002797276,0.0004058849,0.001068206,0.000627992,0.001650485],"category_scores_gemma":[0.0009554943,0.0003135047,0.0004146087,0.0001531559,0.0005508077,0.000482925,0.0007611064,0.0010823,0.0002982213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003807883,"about_ca_system_score_gemma":0.0006677452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003690706,"about_ca_topic_score_gemma":0.002671518,"domain_scores_codex":[0.9997379,0.00005909618,0.00001227207,0.00005489721,0.0001031572,0.00003259489],"domain_scores_gemma":[0.9996644,0.0001326439,0.00007240794,0.00003692217,0.00006967762,0.00002387203],"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":[0.00003919298,0.0000334804,0.0001777718,0.00005855933,0.00001673493,0.00006234078,0.00005345206,0.9533989,0.004272988,0.005182318,0.0002945389,0.03640972],"study_design_scores_gemma":[0.000003886546,0.00002583258,0.000026298,0.00000218251,0.000001693644,0.000007705696,0.000001747249,0.9987279,0.0003744461,0.0005865109,0.0002395688,0.000002255072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008756326,0.00008486941,0.9891857,0.00005970586,0.00001744769,0.00002057323,0.00000727068,0.000255435,0.00161262],"genre_scores_gemma":[0.8485413,0.000127461,0.1472776,0.0000689888,0.0000340683,0.0001402761,0.00003772171,0.00005551521,0.003717006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003690706,"threshold_uncertainty_score":0.007338464,"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."}}