{"id":"W4293370597","doi":"10.1109/lra.2022.3196132","title":"Safe-Control-Gym: A Unified Benchmark Suite for Safe Learning-Based Control and Reinforcement Learning in Robotics","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dynamic Systems Analysis (Canada); Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Suite; Benchmark (surveying); Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003917353,0.003525279,0.001172202,0.002361752,0.0007530675,0.001786258,0.004270894,0.001883628,0.004917997],"category_scores_gemma":[0.01080441,0.000658899,0.001205617,0.002420015,0.000896565,0.001388412,0.001869456,0.002313142,0.00175055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001635165,"about_ca_system_score_gemma":0.002670047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01607153,"about_ca_topic_score_gemma":0.0161859,"domain_scores_codex":[0.9964227,0.001206645,0.0003572492,0.0003803386,0.001228555,0.0004043532],"domain_scores_gemma":[0.9945082,0.002321275,0.0003688817,0.0007939968,0.001582873,0.0004249067],"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":[0.000987038,0.001375449,0.004930566,0.002274076,0.0003314166,0.0003415289,0.0001674172,0.6457854,0.004969455,0.02275209,0.1457145,0.1703711],"study_design_scores_gemma":[0.0004829893,0.0006206548,0.002063132,0.0001734307,0.00006504506,0.0001520173,0.0001049619,0.914008,0.01095062,0.01271989,0.05859458,0.00006472033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2341814,0.00872069,0.5439245,0.003586483,0.00219546,0.002613581,0.05597841,0.06382599,0.08497339],"genre_scores_gemma":[0.4478377,0.002944429,0.4081267,0.001087362,0.0001966859,0.003319223,0.1159025,0.006382408,0.01420294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01607153,"threshold_uncertainty_score":0.03195596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009230860443678211,"score_gpt":0.2213084829775076,"score_spread":0.2120776225338294,"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."}}