{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006982667,0.0004166679,0.0005011176,0.000266429,0.0002401731,0.0009496989,0.000862264,0.0003002907,0.00357529],"category_scores_gemma":[0.006748942,0.0003797415,0.0002161372,0.0006225616,0.0002036462,0.002184865,0.0002352664,0.0003515248,0.002197919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003849747,"about_ca_system_score_gemma":0.0008592218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001065493,"about_ca_topic_score_gemma":0.0003043806,"domain_scores_codex":[0.9941453,0.001091935,0.001476266,0.001140738,0.001110169,0.001035595],"domain_scores_gemma":[0.9924518,0.004303102,0.0003823139,0.0009751383,0.001566752,0.0003208797],"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":[0.0001965059,0.002177882,0.002316334,0.0000779931,0.0001705334,0.00001808406,0.00385791,0.01906218,0.006162828,0.3077568,0.02976286,0.6284401],"study_design_scores_gemma":[0.0008029004,0.000348083,0.0009687483,0.00004622214,0.00007772697,0.000007535964,0.0002856607,0.8928628,0.005156446,0.09710406,0.001932205,0.0004075994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008943833,0.0001945984,0.9571782,0.0245811,0.002095459,0.005300235,0.000008370504,0.00008696602,0.001611171],"genre_scores_gemma":[0.8757948,0.00003737391,0.119897,0.002171997,0.0003165612,0.001124803,0.000005752085,0.00002598445,0.0006257259],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8738006,"threshold_uncertainty_score":0.9998655,"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."}}