{"id":"W66652580","doi":"10.5555/2484920.2485079","title":"Baseline: practical control variates for agent evaluation in zero-sum domains","year":2013,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Variance reduction; Control variates; Baseline (sea); Variance (accounting); Computer science; Reduction (mathematics); Estimator; Monte Carlo method; Domain (mathematical analysis); Overhead (engineering); Algorithm; Mathematical optimization; Artificial intelligence; Statistics; Mathematics; Hybrid Monte Carlo","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":[0.001941723,0.0001058623,0.0001350039,0.00008644982,0.00005998059,0.0002030383,0.0003429906,0.00006663272,0.0003906233],"category_scores_gemma":[0.001744484,0.00008690285,0.00005181894,0.0001897216,0.00003364618,0.0008193163,0.0000661118,0.00008504395,0.000522871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008787192,"about_ca_system_score_gemma":0.0001384595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000289786,"about_ca_topic_score_gemma":0.00009996531,"domain_scores_codex":[0.998455,0.000208082,0.0003587505,0.0003355746,0.0003471091,0.0002955113],"domain_scores_gemma":[0.9978374,0.00129151,0.00007782939,0.0003586477,0.0003544927,0.00008010917],"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":[0.00003863581,0.0006153382,0.002520475,0.00001672025,0.00004419709,0.000006526768,0.001326742,0.00657698,0.00917777,0.688296,0.03184469,0.2595359],"study_design_scores_gemma":[0.0002416382,0.00006741874,0.000863204,0.000005399355,0.000007687984,0.000002220989,0.00006009817,0.89166,0.004682281,0.1010263,0.001275012,0.0001087884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008323501,0.00002147706,0.9782416,0.01041053,0.000372987,0.001276869,0.000001065355,0.0000817196,0.001270217],"genre_scores_gemma":[0.8280344,0.000002737843,0.1701368,0.001134606,0.00006605867,0.0004336661,0.000001949928,0.00000603493,0.0001837982],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.885083,"threshold_uncertainty_score":0.6720623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0631569794152325,"score_gpt":0.359566842125435,"score_spread":0.2964098627102025,"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."}}