{"id":"W2151123669","doi":"10.5555/1838206.1838229","title":"Using counterfactual regret minimization to create competitive multiplayer poker agents","year":2010,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Perfect information; Computer science; Regret; Counterfactual thinking; Nash equilibrium; Extensive-form game; Mathematical economics; Strategy; Best response; Bayesian game; Complete information; Repeated game; Game theory; Mathematics; 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":[0.004142333,0.0008209516,0.0006129926,0.0006798526,0.0007302848,0.00124694,0.002269549,0.001087069,0.002660765],"category_scores_gemma":[0.008879366,0.0004059929,0.0006465415,0.00035453,0.001744281,0.001184647,0.002748284,0.001256544,0.0003457654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101672,"about_ca_system_score_gemma":0.0008024682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008703554,"about_ca_topic_score_gemma":0.00119571,"domain_scores_codex":[0.9979698,0.0009818142,0.00008337458,0.000251288,0.0005401727,0.0001734113],"domain_scores_gemma":[0.9950846,0.002830952,0.000580738,0.0008128457,0.0004385149,0.0002523047],"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":[0.0004754345,0.0007327617,0.003431761,0.000100287,0.0001417501,0.0003859029,0.0007330385,0.7725523,0.009401439,0.1423612,0.001334054,0.06835017],"study_design_scores_gemma":[0.00007612152,0.0002248832,0.0002494763,0.000009971097,0.00002442149,0.00007814869,0.00004750534,0.9631717,0.005046641,0.02904719,0.002007485,0.00001642336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2904204,0.00010707,0.6927014,0.0004035583,0.00007133294,0.0005199612,0.00006499232,0.0006711014,0.0150402],"genre_scores_gemma":[0.7295814,0.00003661441,0.2658377,0.0001503685,0.00001400103,0.0004675373,0.00007348393,0.00007082189,0.003768225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004142333,"threshold_uncertainty_score":0.02190697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0745210933639978,"score_gpt":0.3409293452544012,"score_spread":0.2664082518904033,"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."}}