{"id":"W3164043830","doi":"10.2514/1.i010921","title":"Human-Aware Reinforcement Learning for Fault Recovery Using Contextual Gaussian Processes","year":2021,"lang":"en","type":"article","venue":"Journal of Aerospace Information Systems","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Defense Advanced Research Projects Agency; National Aeronautics and Space Administration","keywords":"Forgetting; Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Robot; Process (computing); Set (abstract data type); Machine learning; Gaussian process; Human–robot interaction; Baseline (sea); Gaussian; Engineering","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000612794,0.0001755418,0.0003664598,0.0001928995,0.0003350894,0.001235036,0.0004653761,0.0001042957,0.000008022269],"category_scores_gemma":[0.0003455748,0.0001488428,0.0001238788,0.0004980183,0.00002253356,0.005637411,0.00009030044,0.0002408326,0.00000995879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001551839,"about_ca_system_score_gemma":0.000901025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000136259,"about_ca_topic_score_gemma":0.00000402219,"domain_scores_codex":[0.9978274,0.00005108621,0.001142795,0.0001221909,0.000569803,0.0002867158],"domain_scores_gemma":[0.9953324,0.00008581618,0.001820822,0.0002119819,0.002412271,0.0001366692],"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":[0.0001265037,0.0001338283,0.001413555,0.006581181,0.0003860622,0.00007122875,0.01508214,0.9007033,0.002931324,0.04787631,0.009438244,0.01525631],"study_design_scores_gemma":[0.008272891,0.003517387,0.0006119965,0.00790748,0.0001816689,0.005261134,0.03678983,0.7143251,0.01931042,0.001187097,0.2004952,0.002139724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008670554,0.0002729516,0.9887397,0.0003743081,0.0007659805,0.0002191976,0.000002677056,0.00003839804,0.0009161813],"genre_scores_gemma":[0.9918993,0.00004507088,0.007243311,0.0001636508,0.0001916328,0.00001035751,0.000007729279,0.000007022786,0.0004319996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9832287,"threshold_uncertainty_score":0.9998018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02755522201738358,"score_gpt":0.2802436116144039,"score_spread":0.2526883895970203,"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."}}