{"id":"W3037507370","doi":"10.65109/hjfz7394","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of ƒ-Regression Counterfactual Regret Minimization","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"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; Approximation algorithm; Mathematical optimization; Computer science; Function (biology); Mathematics; Applied mathematics; Mathematical economics; Artificial intelligence; Artificial neural network; Machine learning","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":[0.0008279207,0.0001537784,0.0004277904,0.0007131745,0.0001681029,0.0001865764,0.0004417168,0.0001146579,0.000649532],"category_scores_gemma":[0.004886107,0.0001092595,0.0002054465,0.002763543,0.00009919393,0.00133261,0.00008081588,0.0001159119,0.00001392837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000542094,"about_ca_system_score_gemma":0.00006180377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001941316,"about_ca_topic_score_gemma":0.00002645002,"domain_scores_codex":[0.9968563,0.000165454,0.0007781563,0.0006253651,0.001364635,0.0002101153],"domain_scores_gemma":[0.9963009,0.001313283,0.0005334835,0.0003952419,0.001305723,0.0001513115],"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":[0.0008800055,0.0002159398,0.0039353,0.00002745262,0.0006201503,8.834721e-7,0.006478885,0.8955401,0.0100226,0.001962022,0.001119058,0.07919757],"study_design_scores_gemma":[0.0004090972,0.000399708,0.002227684,0.000008055945,0.0001714402,2.04969e-7,0.002567073,0.9831156,0.007279735,0.003327365,0.0003734612,0.0001205797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07203786,0.00001686755,0.9267403,0.000351497,0.0001048169,0.0004650014,0.0001392801,0.00004925187,0.00009513975],"genre_scores_gemma":[0.9691979,0.000009762889,0.0298926,0.0001738798,0.00008465558,0.0000508284,0.0003953124,0.0000154844,0.0001796363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.89716,"threshold_uncertainty_score":0.711192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1977424699238212,"score_gpt":0.4430128260052182,"score_spread":0.245270356081397,"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."}}