{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002977577,0.0001655165,0.0001921136,0.00009832467,0.0005434271,0.0002876874,0.00056528,0.00005820289,0.0003530651],"category_scores_gemma":[0.0008517132,0.00007330171,0.00006645839,0.0006451419,0.0004844212,0.001009841,0.00007513092,0.0002295049,0.000243046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008333088,"about_ca_system_score_gemma":0.0001526719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002907114,"about_ca_topic_score_gemma":0.0001744489,"domain_scores_codex":[0.9962276,0.0002128997,0.0004116752,0.0003541097,0.002110003,0.0006837569],"domain_scores_gemma":[0.9963703,0.002316942,0.00008663452,0.0005543497,0.0004650058,0.0002067226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003659212,0.00194675,0.003979241,0.00004493809,0.0003031863,0.00003000471,0.03589255,0.2181226,0.0006472697,0.1430362,0.02297327,0.5693648],"study_design_scores_gemma":[0.009003382,0.004892909,0.01779954,0.0002132172,0.0001717683,0.0004210011,0.06305399,0.1886163,0.002202982,0.493261,0.2172256,0.00313839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01582341,0.0001866468,0.9742786,0.00188634,0.0003547717,0.001226383,0.00001557226,0.0001149176,0.00611339],"genre_scores_gemma":[0.9885115,0.000004254697,0.00584606,0.00004381794,0.0003620601,0.0001305036,0.000004008111,0.00001712318,0.005080652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9726881,"threshold_uncertainty_score":0.4179657,"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."}}