{"id":"W1526654727","doi":"","title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Upper and lower bounds; Logarithm; Computer science; Probably approximately correct learning; Markov process; Sample complexity; Contrast (vision); Binary logarithm; Exploratory analysis; Q-learning; Algorithm; Exploratory research; Markov chain; Process (computing); Mathematics; Artificial intelligence; Combinatorics; Machine learning; Active learning (machine learning); Computational learning theory; 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":[],"consensus_categories":[],"category_scores_codex":[0.000355473,0.0002031208,0.0001596532,0.0001248,0.0003965572,0.0005844307,0.0007089482,0.0000787195,0.0001202743],"category_scores_gemma":[0.00004230235,0.000164137,0.00004744922,0.0003302954,0.0001340729,0.001367597,0.0001502931,0.0005463532,0.0001340151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004668139,"about_ca_system_score_gemma":0.0002037185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003820553,"about_ca_topic_score_gemma":0.00004837982,"domain_scores_codex":[0.9983113,0.00004036175,0.0002856723,0.0003735695,0.0006139561,0.0003751881],"domain_scores_gemma":[0.998732,0.00005212837,0.0001680237,0.0007122034,0.0001949375,0.0001406833],"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":[0.000009412914,0.00001235423,0.0005091875,0.000006977421,0.00000751931,0.000002061407,0.0003028775,0.8894727,0.0008206456,0.1081614,0.0001662793,0.0005285315],"study_design_scores_gemma":[0.0004881223,0.0002984998,0.0001785046,0.00001032042,0.000005571679,0.000002613026,0.00001748834,0.9929459,0.001719813,0.0005594099,0.003522617,0.0002511253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004982404,0.000001216223,0.9684016,0.0009013081,0.000188221,0.0002137315,1.024891e-7,0.000496041,0.02481536],"genre_scores_gemma":[0.7391004,6.870097e-7,0.2566486,0.0003726105,0.00003504305,0.00001830303,0.00001818807,0.00001364213,0.003792538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.734118,"threshold_uncertainty_score":0.6693313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04441804103927028,"score_gpt":0.2579625849142766,"score_spread":0.2135445438750063,"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."}}