{"id":"W2993775923","doi":"10.48550/arxiv.1912.02967","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Softmax function; Counterfactual thinking; Approximation error; Function approximation; Reinforcement learning; Perfect information; Function (biology); Mathematics; Mathematical optimization; Computer science; Applied mathematics; Mathematical economics; Artificial intelligence; Statistics; Artificial neural network","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":[0.0140761,0.002467967,0.002363786,0.001691043,0.0009493401,0.002943609,0.003650869,0.003118195,0.003956228],"category_scores_gemma":[0.06429777,0.0008354333,0.001945363,0.001651159,0.003652055,0.006200381,0.003507158,0.006049038,0.0006695278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004286962,"about_ca_system_score_gemma":0.002425356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003226097,"about_ca_topic_score_gemma":0.002393832,"domain_scores_codex":[0.9922989,0.004468318,0.0002536356,0.0008806741,0.001487348,0.0006111099],"domain_scores_gemma":[0.9751726,0.0193719,0.001554835,0.002333612,0.001082126,0.0004848654],"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":[0.0001750056,0.0001489428,0.00104194,0.0001505283,0.00009999365,0.00007044213,0.0001561984,0.7037648,0.000803295,0.2570038,0.002138061,0.03444707],"study_design_scores_gemma":[0.00001825211,0.0000517948,0.0001073741,0.00003589524,0.00001672523,0.00002390208,0.00001832278,0.9438749,0.0004138193,0.0548316,0.0005950335,0.00001237129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01903906,0.0006363337,0.9724521,0.0009588195,0.00004848902,0.0001192108,0.00007016851,0.0003376563,0.006338266],"genre_scores_gemma":[0.6472291,0.001150695,0.3430496,0.00113402,0.0001702662,0.0007840394,0.0002806546,0.000510389,0.005691191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0140761,"threshold_uncertainty_score":0.07444239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2439719094393615,"score_gpt":0.3377391204489972,"score_spread":0.0937672110096357,"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."}}