{"id":"W4294912101","doi":"10.36227/techrxiv.14842245.v2","title":"Safe Deployment of a Reinforcement Learning Robot Using Self Stabilization","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Software deployment; Robot; Robotics; Computer science; State space; Artificial intelligence; Simulation; Human–computer interaction; Software engineering; Mathematics","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":[0.0007685639,0.0007342673,0.0003873622,0.0002648513,0.0003296574,0.0004480862,0.0008837041,0.0007822989,0.001500156],"category_scores_gemma":[0.002972065,0.0002783869,0.0002901025,0.0001009799,0.001160511,0.0005086334,0.001187845,0.0008473041,0.0004159234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005273646,"about_ca_system_score_gemma":0.0009656211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003212707,"about_ca_topic_score_gemma":0.00217653,"domain_scores_codex":[0.9995074,0.0001281062,0.00002552963,0.0001151656,0.0001484072,0.00007538217],"domain_scores_gemma":[0.9984471,0.0006055076,0.0002953004,0.0002542912,0.0002457938,0.0001520642],"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":[0.0001808686,0.00009383384,0.0007739831,0.00006189619,0.00002117623,0.0002293907,0.0001694369,0.9369518,0.02337124,0.005555195,0.0006066131,0.03198461],"study_design_scores_gemma":[0.00001584956,0.00009281741,0.00008058528,0.000004395527,0.000002974315,0.00001702463,0.00000855798,0.9958389,0.002792671,0.0008993208,0.0002430521,0.000003865729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09245086,0.00006517352,0.9024655,0.0001787205,0.00003842078,0.0001046835,0.00001545577,0.001768345,0.002912895],"genre_scores_gemma":[0.9571936,0.00002268405,0.04116837,0.0000422708,0.000007063716,0.00008010061,0.00001992516,0.00005813583,0.001407858],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003212707,"threshold_uncertainty_score":0.006388068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03750498232283737,"score_gpt":0.286013155198828,"score_spread":0.2485081728759906,"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."}}