{"id":"W4400374283","doi":"10.48550/arxiv.2407.02231","title":"Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute of Steel Construction","keywords":"Reinforcement learning; Artificial intelligence; Reinforcement; Computer science; Psychology; Social psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005285402,0.0006533519,0.0006387206,0.0004791489,0.0004394011,0.000520174,0.002954545,0.0007203493,0.00003636834],"category_scores_gemma":[0.000227001,0.000755102,0.0005430238,0.000842308,0.0001521442,0.0003040552,0.005651602,0.002453248,0.00022242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006969724,"about_ca_system_score_gemma":0.0003649656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003934562,"about_ca_topic_score_gemma":0.000003003182,"domain_scores_codex":[0.9963022,0.0001746192,0.0005387634,0.001839935,0.0002873139,0.0008571479],"domain_scores_gemma":[0.996788,0.0004933114,0.0005242151,0.001653487,0.0002542524,0.0002867444],"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":[0.00003559112,0.00002052631,0.00009693798,0.0003058193,0.0001972023,0.00004757063,0.0005391258,0.6097301,0.000001801831,0.3886115,0.0001223288,0.0002915382],"study_design_scores_gemma":[0.0004777195,0.0001951821,0.00002143074,0.0003335575,0.0001889992,0.000004979908,0.0001900791,0.9530625,0.00001370018,0.04184386,0.002914679,0.0007532896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004083574,0.00009544627,0.9840886,0.0001461129,0.001224162,0.001148679,0.000004025371,0.0008986976,0.01198593],"genre_scores_gemma":[0.8886575,0.0002198943,0.1015098,0.0001463017,0.0002627032,0.00001327556,0.0001269009,0.00007949297,0.008984131],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8882491,"threshold_uncertainty_score":0.9998481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06038632336708043,"score_gpt":0.2145446782603009,"score_spread":0.1541583548932204,"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."}}