{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001233347,0.0003376665,0.0008143387,0.00229447,0.0002110769,0.000210766,0.001175516,0.0004841262,0.0002288774],"category_scores_gemma":[0.00164866,0.0003084328,0.0005229596,0.00260351,0.0001997505,0.001161643,0.0005511208,0.0004399217,0.00002247924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000332404,"about_ca_system_score_gemma":0.0002293773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008456037,"about_ca_topic_score_gemma":0.00007814274,"domain_scores_codex":[0.996388,0.00036628,0.0007195013,0.001520197,0.0006801324,0.0003258494],"domain_scores_gemma":[0.9932686,0.001580091,0.001487118,0.00142806,0.002097044,0.0001391034],"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":[0.0003661655,0.0001170404,0.003742697,0.00003682062,0.0005147063,0.000002272692,0.0005456875,0.9909829,0.0001351519,0.001668392,0.00007441171,0.001813782],"study_design_scores_gemma":[0.0005582611,0.000209019,0.003345734,0.00007094484,0.0007755336,2.769726e-7,0.001312316,0.9640228,0.000498026,0.02881772,0.0001021233,0.0002872557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.307689,0.00001863894,0.6906665,0.00001420412,0.0003862372,0.0007081198,0.0004100841,0.00003965409,0.00006759676],"genre_scores_gemma":[0.9946444,0.00006767293,0.002854401,0.00001810324,0.00007040978,0.000008251704,0.001155585,0.00002907444,0.001152116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6878121,"threshold_uncertainty_score":0.9999368,"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."}}