{"id":"W2562174057","doi":"10.1609/aaai.v32i1.11481","title":"AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Games","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Variance reduction; Variance (accounting); Perfect information; Computer science; Estimator; Imperfect; Heuristic; Limit (mathematics); Value (mathematics); Victory; Mathematical optimization; Artificial intelligence; Statistics; Machine learning; Mathematics; Monte Carlo method; Mathematical economics; Economics","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":[0.001985988,0.0002655096,0.0002755251,0.000359231,0.0002148862,0.00033479,0.001787852,0.0001647761,0.00007120514],"category_scores_gemma":[0.001628004,0.00022156,0.0001291457,0.001253325,0.0003177236,0.001843593,0.000256726,0.0002634795,0.0001144585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002207544,"about_ca_system_score_gemma":0.0004133432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001852345,"about_ca_topic_score_gemma":0.00002950291,"domain_scores_codex":[0.9973369,0.00004171338,0.0009614051,0.0005200217,0.0007047591,0.0004351729],"domain_scores_gemma":[0.9969726,0.0001079406,0.0006292965,0.0004348203,0.001762521,0.00009287131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001250514,0.00008781195,0.00005583885,0.00003350558,0.000009238966,5.65429e-8,0.004268103,0.0001782723,0.1040886,0.5749488,0.0005209068,0.3156838],"study_design_scores_gemma":[0.00002603051,0.0003062387,0.00007513958,0.0001975462,0.000008967183,0.000004768973,0.0004138702,0.1100443,0.6350054,0.2534019,0.000344986,0.0001708363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05271537,0.00002601505,0.9309703,0.004992886,0.001551109,0.003613024,0.000005715631,0.0001490247,0.00597654],"genre_scores_gemma":[0.9783582,0.00002200661,0.02074696,0.0001591899,0.0002317208,0.0003649593,0.000001278266,0.00001205569,0.0001036056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9256428,"threshold_uncertainty_score":0.9034954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09062847487418954,"score_gpt":0.3394626692515252,"score_spread":0.2488341943773356,"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."}}