{"id":"W1969276875","doi":"10.1016/j.tcs.2014.09.029","title":"Near-optimal PAC bounds for discounted MDPs","year":2014,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Upper and lower bounds; Markov decision process; Logarithm; Sample complexity; Mathematics; Reinforcement learning; State space; Stochastic matrix; Markov chain; Matrix (chemical analysis); Space (punctuation); Markov process; Mathematical optimization; Applied mathematics; Combinatorics; Computer science; Statistics; Mathematical analysis","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0102659,0.0002010489,0.0003404915,0.0002577129,0.001128494,0.001895366,0.003267357,0.00006454327,0.0002951193],"category_scores_gemma":[0.005638816,0.0001317964,0.0001277447,0.001898443,0.01001484,0.000813044,0.0009645198,0.0002417086,0.000415793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007674432,"about_ca_system_score_gemma":0.0002144769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001963391,"about_ca_topic_score_gemma":8.480578e-7,"domain_scores_codex":[0.9940432,0.0002155752,0.0005118966,0.001120045,0.003109525,0.0009997865],"domain_scores_gemma":[0.9934081,0.003937643,0.0001050587,0.001162785,0.0009205782,0.0004657753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007204263,0.00005991242,0.00009411832,0.000003085466,0.000003106158,0.000002604752,0.0002976786,0.003854122,0.0002526848,0.860999,0.0007684716,0.1335931],"study_design_scores_gemma":[0.0002754093,0.0003173349,0.0006071444,0.000006321325,0.000001948257,0.000009042983,0.00001784096,0.6586541,0.0009045144,0.3322718,0.006789017,0.0001455169],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04665288,0.000007926085,0.9491842,0.001522099,0.0006470817,0.0002910142,0.00001075557,0.0000805261,0.001603544],"genre_scores_gemma":[0.8297389,6.942789e-7,0.1694122,0.0003263806,0.0003304724,0.00001866684,0.000001433308,0.0000128614,0.0001583384],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7830861,"threshold_uncertainty_score":0.9991407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04680964409173786,"score_gpt":0.418173190851378,"score_spread":0.3713635467596401,"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."}}