{"id":"W4247188402","doi":"10.36227/techrxiv.14842245","title":"Safe Deployment of a Reinforcement Learning Robot Using Self Stabilization","year":2021,"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; Computer science; Robotics; Artificial intelligence; State space; 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":[0.0007395119,0.0004013757,0.0005566318,0.0002751164,0.0001446377,0.0004048747,0.00118779,0.0002727039,0.0001760255],"category_scores_gemma":[0.0001723358,0.00041973,0.0002241618,0.0004460823,0.00003797541,0.0003755645,0.004120194,0.0007266807,0.000009394073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004810134,"about_ca_system_score_gemma":0.0006954513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001804375,"about_ca_topic_score_gemma":0.000006516778,"domain_scores_codex":[0.9962972,0.0002505034,0.001174094,0.0007853335,0.001050175,0.0004426397],"domain_scores_gemma":[0.9969306,0.0001059239,0.0010041,0.001322974,0.0005160149,0.0001203652],"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":[0.000003153601,0.00003304826,0.001190237,0.0003295811,0.00009919225,0.00000651615,0.001550935,0.992224,0.0009537009,0.002917774,0.00001409829,0.0006777567],"study_design_scores_gemma":[0.0002573946,0.0001024398,0.0001789504,0.0003439359,0.00005432672,0.000005541658,0.0001334069,0.9921904,0.005853992,0.00004265769,0.0004360581,0.0004008809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00601643,0.0001029741,0.988297,0.00007638217,0.0007715367,0.0005484241,1.808378e-7,0.0003897933,0.00379725],"genre_scores_gemma":[0.5777539,0.0001508439,0.4210809,0.00007120272,0.00004590053,0.00001649502,0.00003499717,0.0000328252,0.0008129178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5717375,"threshold_uncertainty_score":0.9998255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03484376922820494,"score_gpt":0.2772683896775365,"score_spread":0.2424246204493316,"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."}}