{"id":"W7124154598","doi":"10.65109/mwwb2216","title":"Baseline: practical control variates for agent evaluation in zero-sum domains","year":2013,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Variance reduction; Control variates; Baseline (sea); Variance (accounting); Estimator; Reduction (mathematics); Monte Carlo method; Overhead (engineering)","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":[0.01061115,0.00106025,0.001185722,0.001151017,0.0008275022,0.002318248,0.002106595,0.001379116,0.006285802],"category_scores_gemma":[0.03931931,0.0006240199,0.00073461,0.0006744894,0.001428826,0.002968836,0.002848709,0.002535491,0.001186483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001345011,"about_ca_system_score_gemma":0.00189125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002033068,"about_ca_topic_score_gemma":0.00227293,"domain_scores_codex":[0.9938292,0.003241855,0.0003316604,0.0006494608,0.001646913,0.000301013],"domain_scores_gemma":[0.9849846,0.009817747,0.0007289407,0.001931741,0.002163832,0.0003731457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001160065,0.0006441594,0.003957503,0.0003656093,0.0001606659,0.0001619021,0.0003355397,0.3574295,0.01057723,0.1235583,0.007672857,0.4939767],"study_design_scores_gemma":[0.00008916482,0.0001891912,0.000399867,0.00003935894,0.00001617854,0.00004775061,0.00004174645,0.9517625,0.006151659,0.03886659,0.002369049,0.00002705229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007057746,0.0001037797,0.9898826,0.00008801847,0.00003426244,0.00011257,0.00004856328,0.001160368,0.001511922],"genre_scores_gemma":[0.2665501,0.00008654267,0.7298406,0.0001822282,0.00004296427,0.0004892537,0.0002947642,0.0005205042,0.001993075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01061115,"threshold_uncertainty_score":0.05611777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07526867023720975,"score_gpt":0.3682046070428567,"score_spread":0.2929359368056469,"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."}}