{"id":"W7124312491","doi":"10.65109/octa6133","title":"Targeted Search Control in AlphaZero for Effective Policy Improvement","year":2023,"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":"Reinforcement learning; Sample (material); Limiting; Control (management); Value (mathematics); State (computer science); Train; Function (biology)","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":[0.0008759049,0.0007503715,0.00062065,0.00037322,0.0002927096,0.000731319,0.001307664,0.0007286949,0.003073502],"category_scores_gemma":[0.004350616,0.0003992666,0.0003867183,0.0001995053,0.00104227,0.0009133657,0.001308402,0.001813105,0.0005386773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005990872,"about_ca_system_score_gemma":0.001358603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003368333,"about_ca_topic_score_gemma":0.004262794,"domain_scores_codex":[0.9995505,0.00009116828,0.00002503599,0.0001092943,0.0001550248,0.00006897637],"domain_scores_gemma":[0.9988569,0.0006405095,0.0001224331,0.0001410778,0.000157789,0.00008128148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004500119,0.0002634092,0.002866447,0.0001666982,0.00006974991,0.0001439657,0.00030121,0.7901289,0.02143667,0.03144007,0.003023974,0.1497088],"study_design_scores_gemma":[0.00003093754,0.00008424699,0.0001750608,0.00001164804,0.000008017891,0.00002362768,0.00001217539,0.9921669,0.002758117,0.003554233,0.001167726,0.000007296279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07599018,0.0001607322,0.9139106,0.0002013632,0.00006079369,0.0001019371,0.00005361295,0.003337659,0.006183164],"genre_scores_gemma":[0.806674,0.00008953163,0.188627,0.0002783875,0.00002693698,0.0002555183,0.0001107311,0.0003176566,0.003620394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003368333,"threshold_uncertainty_score":0.01028192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0306515821686123,"score_gpt":0.3479757694916265,"score_spread":0.3173241873230142,"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."}}