{"id":"W2006330826","doi":"10.1007/s10994-011-5254-7","title":"Model selection in reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematics; Estimator; Oracle; Bellman equation; Function (biology); Regularization (linguistics); Countable set; Sequence (biology); Combinatorics; Rate of convergence; Discrete mathematics; Mathematical optimization; Computer science; Artificial intelligence; 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":[0.0007216242,0.0002223244,0.0002093377,0.0003540307,0.0002569882,0.0001041984,0.0006113523,0.00009321766,0.0001205005],"category_scores_gemma":[0.0002114064,0.0002308274,0.00005644726,0.0006207123,0.00002503876,0.0006239088,0.0003533966,0.00097225,0.0001206922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001402561,"about_ca_system_score_gemma":0.00005610281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002680055,"about_ca_topic_score_gemma":0.0000318904,"domain_scores_codex":[0.9980894,0.0001728688,0.0004156024,0.0004235083,0.0003762011,0.0005224266],"domain_scores_gemma":[0.9993745,0.00005099835,0.0002081631,0.0002175094,0.00005672291,0.00009208832],"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":[0.000009690553,0.00001458183,0.04922677,0.00001096968,0.000008971184,0.000007598156,0.002684168,0.9377872,0.0004790688,0.006791615,0.00001469348,0.002964642],"study_design_scores_gemma":[0.0003952052,0.0002499803,0.003296698,0.00002753902,0.000004315214,0.00001002968,0.00003269272,0.9940863,0.000327656,0.0002444906,0.001066779,0.0002582959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01163006,0.00003226135,0.9523351,0.00005427527,0.0000875936,0.0001445649,2.475887e-8,0.0004751324,0.03524103],"genre_scores_gemma":[0.9450121,0.00002299886,0.04760224,0.0001200191,0.0000261649,0.00001701222,0.000004783786,0.00002597894,0.007168737],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.933382,"threshold_uncertainty_score":0.9412867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03659510899503107,"score_gpt":0.2458099770528048,"score_spread":0.2092148680577738,"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."}}