{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003476276,0.001342127,0.00169479,0.0007699728,0.0006499314,0.001858947,0.001478286,0.002295542,0.002701613],"category_scores_gemma":[0.01662057,0.0006903355,0.001175767,0.0007078697,0.003284961,0.002313868,0.001996123,0.003949914,0.000462801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002398215,"about_ca_system_score_gemma":0.001614204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003695175,"about_ca_topic_score_gemma":0.001901831,"domain_scores_codex":[0.9981,0.0009207575,0.00009436904,0.0003532899,0.0004158122,0.0001158322],"domain_scores_gemma":[0.9909371,0.007472861,0.0004745921,0.0004075612,0.0005204784,0.0001874797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006746827,0.00006810542,0.0008311051,0.0002923587,0.0001034044,0.00008805608,0.0001197766,0.5756539,0.0008173934,0.3855309,0.002386743,0.03404091],"study_design_scores_gemma":[0.0000205173,0.00004009747,0.0001098564,0.00003523994,0.00001217596,0.00002047994,0.000009942622,0.8430735,0.0002364512,0.1543582,0.002071112,0.00001236761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006707109,0.00210168,0.9820096,0.001223912,0.0001951019,0.00005763496,0.00004232836,0.0001435323,0.007519045],"genre_scores_gemma":[0.6577846,0.004495672,0.320766,0.00121264,0.00105825,0.000722755,0.0002359872,0.0002673695,0.01345668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003695175,"threshold_uncertainty_score":0.01838452,"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."}}