{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001045085,0.0003907782,0.0004952146,0.0003830626,0.0002659507,0.0002068717,0.001689342,0.0001712356,0.0007181141],"category_scores_gemma":[0.0001227476,0.0004186032,0.000208227,0.0004813871,0.00003609479,0.0002797673,0.00679748,0.0009616518,0.00001128405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008065747,"about_ca_system_score_gemma":0.0005492633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001990975,"about_ca_topic_score_gemma":0.000002577244,"domain_scores_codex":[0.9959981,0.0003078866,0.001165733,0.0007608181,0.001316595,0.0004508254],"domain_scores_gemma":[0.9970493,0.0001211038,0.001170615,0.001318363,0.0002335596,0.0001070265],"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":[0.000006085351,0.00003351778,0.001546066,0.0002360661,0.00008165665,0.000003818077,0.001349746,0.9875683,0.0002723422,0.008348975,0.00003826245,0.000515234],"study_design_scores_gemma":[0.0002720501,0.0001993341,0.0001456447,0.00009342626,0.00004744335,0.000003451373,0.000106485,0.9940839,0.0009301718,0.0001338529,0.003578896,0.0004053426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002331375,0.00006212622,0.9874425,0.00008516848,0.0009072704,0.0007723593,5.163656e-7,0.0005039216,0.007894778],"genre_scores_gemma":[0.578265,0.0001569509,0.4184684,0.0001200022,0.00006101006,0.00006633573,0.0000590601,0.00005896895,0.002744258],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5759336,"threshold_uncertainty_score":0.9998266,"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."}}