{"id":"W3101144313","doi":"","title":"Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Regret; Markov decision process; Bounding overwatch; Inverse; Combinatorics; Adversarial system; Hessian matrix; Mathematics; Markov chain; Robustness (evolution); Computer science; Diagonal; Discrete mathematics; Markov process; Mathematical optimization; Artificial intelligence; Applied 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":[0.002559038,0.001387584,0.002093473,0.0004370077,0.0005515495,0.001620264,0.002501992,0.002728998,0.002553814],"category_scores_gemma":[0.01116312,0.0007821785,0.0007650433,0.0005846416,0.001907771,0.003123708,0.002253848,0.003290339,0.0004990075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001537969,"about_ca_system_score_gemma":0.001645342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003822925,"about_ca_topic_score_gemma":0.003858646,"domain_scores_codex":[0.9988888,0.0003714042,0.00005278028,0.0003478866,0.0001542474,0.0001849321],"domain_scores_gemma":[0.9926412,0.005807964,0.0005681352,0.0004713839,0.000209702,0.0003016917],"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":[0.0001724895,0.00005462463,0.000629768,0.00005504912,0.00004068465,0.00006131962,0.0000424073,0.9617857,0.0002617198,0.0250448,0.0006910369,0.01116039],"study_design_scores_gemma":[0.00001399059,0.00001772035,0.00004030119,0.000005212793,0.000005012655,0.000008412994,0.000004900162,0.9879084,0.0001642127,0.01170082,0.000127295,0.000003736948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06190582,0.0004263716,0.9325509,0.001223651,0.00007273914,0.0000852957,0.0001779612,0.0005368414,0.003020351],"genre_scores_gemma":[0.9127512,0.0002453678,0.08147031,0.0004289969,0.0001204075,0.0001822855,0.0002994428,0.00008227496,0.004419743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003822925,"threshold_uncertainty_score":0.01353365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05573393714338376,"score_gpt":0.3323731971055618,"score_spread":0.276639259962178,"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."}}