{"id":"W4316464918","doi":"10.3390/robotics12010012","title":"Simulated and Real Robotic Reach, Grasp, and Pick-and-Place Using Combined Reinforcement Learning and Traditional Controls","year":2023,"lang":"en","type":"article","venue":"Robotics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Korea Electrotechnology Research Institute","keywords":"Reinforcement learning; GRASP; Task (project management); Artificial intelligence; Robotics; Computer science; Robot; Control (management); Plan (archaeology); Margin (machine learning); Human–computer interaction; Machine learning; Engineering; Software engineering; Systems 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000541715,0.0002928676,0.0003976569,0.000219501,0.0004875838,0.0004017565,0.000190327,0.000143113,0.000004522433],"category_scores_gemma":[0.0001917675,0.0003007691,0.00003345045,0.0003751116,0.0002079164,0.0004251853,0.0004151706,0.0003705207,0.000006364497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006557628,"about_ca_system_score_gemma":0.00006223736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000565636,"about_ca_topic_score_gemma":0.00000383865,"domain_scores_codex":[0.9979825,0.0001300002,0.0004512741,0.0005113409,0.0004287024,0.0004961534],"domain_scores_gemma":[0.9985449,0.0006621974,0.000206561,0.0002536974,0.00008541066,0.000247173],"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":[0.00001890077,0.000009481034,0.005964671,0.00006067679,0.00005613329,0.00002642704,0.0004747181,0.9690546,0.0003490223,0.02345804,0.00004518896,0.0004821573],"study_design_scores_gemma":[0.001572768,0.0003681227,0.007359562,0.00008782505,0.00006315106,0.00005915155,0.00009193832,0.9892778,0.00002183218,0.0006898993,0.00008656539,0.0003213612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1642755,0.0002043132,0.8323089,0.001293599,0.0003341601,0.000625165,0.000001300324,0.0005172121,0.0004399201],"genre_scores_gemma":[0.981108,0.0006102253,0.01712374,0.0001239812,0.00006096049,0.000003490974,0.0000324216,0.00003154746,0.0009056194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8168325,"threshold_uncertainty_score":0.9999444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03761961539231777,"score_gpt":0.2666588043082793,"score_spread":0.2290391889159615,"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."}}