{"id":"W2241126168","doi":"","title":"The adversarial stochastic shortest path problem with unknown transition probabilities","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Markov decision process; Reinforcement learning; Shortest path problem; Computer science; Logarithm; State space; Mathematical optimization; Mathematics; Graph; Markov process; Artificial intelligence; Theoretical computer science; Machine learning","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":[0.001669297,0.001025662,0.001479176,0.000522365,0.0005229615,0.001082528,0.001665679,0.00192458,0.002106568],"category_scores_gemma":[0.006066394,0.0005004141,0.0006960881,0.0006602083,0.001672554,0.002259821,0.001324469,0.001782609,0.0002611676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001193734,"about_ca_system_score_gemma":0.001315853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003203357,"about_ca_topic_score_gemma":0.001964786,"domain_scores_codex":[0.9988499,0.0004604275,0.00004313652,0.0003585505,0.0001426813,0.0001454029],"domain_scores_gemma":[0.9959689,0.002974952,0.0004867878,0.0002217527,0.0001352033,0.0002123471],"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":[0.00005957072,0.00003108042,0.0002858558,0.00003476649,0.00002919198,0.00007847462,0.00002687581,0.966005,0.0002870288,0.02720506,0.000386792,0.005570294],"study_design_scores_gemma":[0.000009935879,0.00001485112,0.0000407769,0.000002716243,0.000004061915,0.00001190139,0.000003677359,0.9778431,0.0001357234,0.02172738,0.0002022558,0.000003626207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03639945,0.0002310515,0.9605227,0.0005289506,0.00004484212,0.00005479519,0.0001272511,0.0001566988,0.001934334],"genre_scores_gemma":[0.874408,0.0004059827,0.1198192,0.0001799158,0.0001116233,0.0001863863,0.0002767055,0.00007819774,0.004534002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003203357,"threshold_uncertainty_score":0.008828223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06434972756859121,"score_gpt":0.3637676920026717,"score_spread":0.2994179644340805,"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."}}