{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006158337,0.001042441,0.001336949,0.0006787491,0.0004175999,0.001243266,0.002147925,0.00179186,0.002151751],"category_scores_gemma":[0.03817083,0.0008416369,0.0007174442,0.0005663529,0.002556771,0.002783545,0.003336858,0.002883213,0.0003122697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0014286,"about_ca_system_score_gemma":0.001037748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003158295,"about_ca_topic_score_gemma":0.001402464,"domain_scores_codex":[0.9980863,0.0009404562,0.00007469205,0.0003774223,0.0003108716,0.0002102466],"domain_scores_gemma":[0.9692256,0.02767727,0.0009925758,0.00113135,0.0006524355,0.0003206594],"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":[0.0001271191,0.0000367906,0.0005426401,0.00005071614,0.0000443325,0.00004037259,0.00005132812,0.9654176,0.001237014,0.01446219,0.0003596644,0.01763013],"study_design_scores_gemma":[0.000004257834,0.00002568706,0.00008843229,0.000005389725,0.000003855649,0.000007729501,0.000004286075,0.9896888,0.0003054541,0.00981105,0.00005154778,0.000003471353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08213944,0.0005928885,0.9121023,0.0006959392,0.00005609168,0.00004244805,0.00007240771,0.0006304925,0.003667986],"genre_scores_gemma":[0.9552046,0.000261672,0.04059702,0.0001760806,0.00007718606,0.00007764053,0.0001645945,0.0002252125,0.003215887],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006158337,"threshold_uncertainty_score":0.03256881,"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."}}