{"id":"W4386811899","doi":"10.1007/978-3-031-43424-2_3","title":"Exploring the Training Robustness of Distributional Reinforcement Learning Against Noisy State Observations","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Bounded function; Mathematical optimization; Artificial intelligence; Markov decision process; Suite; Algorithm; Markov process; Mathematics; Statistics","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":[0.002116836,0.0005068877,0.000552244,0.0006152714,0.0008149096,0.0003558597,0.003586064,0.0001300879,0.000006204459],"category_scores_gemma":[0.0007076621,0.0004235823,0.0001815241,0.001402818,0.0007689194,0.001135166,0.002240916,0.00169215,0.0000115349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000368844,"about_ca_system_score_gemma":0.0007549087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002534536,"about_ca_topic_score_gemma":0.00003267579,"domain_scores_codex":[0.9955786,0.00009501506,0.0008621168,0.001122554,0.001570417,0.0007713113],"domain_scores_gemma":[0.996152,0.001590468,0.0006562525,0.001075322,0.0004023073,0.0001236458],"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":[0.000003357436,0.000004957021,0.00005522511,0.00002567691,0.00001656457,0.00001349464,0.001783862,0.8350669,0.00005108309,0.01774091,0.000002520773,0.1452354],"study_design_scores_gemma":[0.0002059282,0.00006819784,0.000689171,0.0005011032,0.000009171203,0.000007816937,0.000003807872,0.9874462,0.0001955997,0.01001072,0.0004027011,0.0004595131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001348565,0.00002965819,0.9939578,0.0008852174,0.002644979,0.0003566394,0.000005644487,0.0002653795,0.0005060839],"genre_scores_gemma":[0.7729391,0.000132615,0.2242527,0.0003500436,0.0009399939,0.00007388368,0.00007697607,0.0001047945,0.00112986],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7715906,"threshold_uncertainty_score":0.9998216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025455228534757,"score_gpt":0.2689238549056029,"score_spread":0.1663783320521272,"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."}}