{"id":"W2460675832","doi":"10.7939/r34p5w","title":"Regularization in reinforcement learning","year":2011,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Minimax; Regularization (linguistics); Mathematical optimization; Bellman equation; Estimator; Computer science; Mathematics; Algorithm; Markov process; Artificial intelligence","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004936125,0.0002404538,0.000223389,0.0005768396,0.0001658783,0.0001009792,0.0007277058,0.0001618898,0.00003540389],"category_scores_gemma":[0.0002278519,0.0002639832,0.00005828743,0.001103338,0.00004839438,0.001112554,0.0003443346,0.0003739806,0.0000236326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004943458,"about_ca_system_score_gemma":0.0001257295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001109308,"about_ca_topic_score_gemma":0.0002405966,"domain_scores_codex":[0.9980732,0.0001389812,0.000441645,0.0004992621,0.0003029516,0.0005439743],"domain_scores_gemma":[0.9987115,0.00004373554,0.0002307174,0.0007022741,0.00014568,0.0001660624],"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":[0.0000454328,0.0002555254,0.0174304,0.00001677677,0.00002309225,0.0001086553,0.003137685,0.5921095,0.002128905,0.3299554,0.00008623138,0.05470239],"study_design_scores_gemma":[0.0004969328,0.0001271257,0.01417273,0.00002877859,0.000003487679,0.00003284027,0.00005760978,0.9669902,0.01015923,0.007237183,0.0003786355,0.0003152324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008733668,0.0001083269,0.9926488,0.0003128029,0.0001048579,0.0005130943,6.174602e-7,0.0007894901,0.00464865],"genre_scores_gemma":[0.3265229,0.00007457582,0.6703011,0.0005284136,0.00002465143,0.0002234469,0.000009062836,0.000030735,0.002285149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3748807,"threshold_uncertainty_score":0.9999812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01399523056772658,"score_gpt":0.2286204980171971,"score_spread":0.2146252674494706,"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."}}