{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006617566,0.0001772267,0.0002885192,0.0002170327,0.0004638447,0.001417773,0.0002598576,0.00008305565,0.00002285542],"category_scores_gemma":[0.001617753,0.0001242273,0.00003076376,0.0008631811,0.0001330372,0.004224517,0.00004557957,0.0003768529,0.0001312408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000442068,"about_ca_system_score_gemma":0.0001069664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001947358,"about_ca_topic_score_gemma":0.000001808718,"domain_scores_codex":[0.9970074,0.0001508388,0.000714143,0.0002777918,0.001556882,0.0002929909],"domain_scores_gemma":[0.9981296,0.0004452195,0.0004042597,0.0001226448,0.0006789387,0.0002193383],"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":[0.0002377037,0.000005268516,0.00003253169,0.0001123589,0.000005266985,0.000007305312,0.00860553,0.8793265,0.00006627895,0.00002313796,0.0001033393,0.1114748],"study_design_scores_gemma":[0.0008387713,0.0003253031,0.0000438341,0.00006481864,0.000007857991,0.0001016987,0.005735172,0.9872134,0.00002349407,0.00004048593,0.005439867,0.0001652838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05685963,0.0001902869,0.9401946,0.001385253,0.0001899182,0.000573693,0.00001276668,0.0002158414,0.0003780277],"genre_scores_gemma":[0.9991298,0.000002075646,0.0002960372,0.0002155858,0.0002009359,0.00002198808,0.00002076854,0.00001179099,0.0001010631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9422701,"threshold_uncertainty_score":0.9996188,"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."}}