{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008986343,0.0006971778,0.0006355667,0.0003280656,0.0002932548,0.000617579,0.001811056,0.0009601352,0.003395439],"category_scores_gemma":[0.001188939,0.0003557417,0.0005021167,0.0001563272,0.0006940603,0.0006127055,0.001337116,0.001190922,0.0006040783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008753893,"about_ca_system_score_gemma":0.001311498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005913796,"about_ca_topic_score_gemma":0.006228687,"domain_scores_codex":[0.9997115,0.00008042962,0.00001007146,0.00006341052,0.00008113972,0.00005344286],"domain_scores_gemma":[0.9996095,0.0001345356,0.00004457859,0.00005224316,0.0001037714,0.00005541318],"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":[0.00007018585,0.00006440173,0.0004605977,0.0000454366,0.00002661326,0.00006117278,0.00003172981,0.9523709,0.001777395,0.005507688,0.0008229413,0.03876083],"study_design_scores_gemma":[0.000003326608,0.00001622481,0.00002245445,0.000001712476,0.000001466564,0.000004849964,0.00000196269,0.9985921,0.000198827,0.000895696,0.0002601066,0.000001299765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01474563,0.0001859602,0.9800559,0.0001666339,0.00005289697,0.00004701389,0.00003708091,0.001432368,0.003276582],"genre_scores_gemma":[0.8106812,0.0001230127,0.1829769,0.0002024791,0.00004280039,0.0001798605,0.0001406157,0.000199152,0.005454058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005913796,"threshold_uncertainty_score":0.01175874,"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."}}