{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01367869,0.00226531,0.002333883,0.001527394,0.000886129,0.002682928,0.003565849,0.002612564,0.003746027],"category_scores_gemma":[0.05884812,0.0008545614,0.001871922,0.001529388,0.003462533,0.005828843,0.003200648,0.005936126,0.0005963274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003966522,"about_ca_system_score_gemma":0.002384879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003250935,"about_ca_topic_score_gemma":0.002441854,"domain_scores_codex":[0.992976,0.00391219,0.0002388907,0.0007944885,0.001457096,0.0006214544],"domain_scores_gemma":[0.9768035,0.01798653,0.001609525,0.002041486,0.001081347,0.0004776492],"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":[0.0001451022,0.0001228441,0.0008457542,0.0001307324,0.00008910045,0.00006338501,0.0001511611,0.718221,0.0007760544,0.2526851,0.001643878,0.02512602],"study_design_scores_gemma":[0.00001486419,0.00004460787,0.00009323991,0.00003124567,0.00001506325,0.00002148067,0.00001675902,0.951975,0.000344197,0.04692102,0.0005108246,0.00001169763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01637245,0.0005184147,0.976732,0.0007259783,0.00004035525,0.0001059682,0.0000564503,0.0002485387,0.005199806],"genre_scores_gemma":[0.6459154,0.001103678,0.3443978,0.0009180031,0.0001496966,0.0007513983,0.0002321058,0.0004214066,0.006110574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01367869,"threshold_uncertainty_score":0.07234067,"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."}}