{"id":"W1726776292","doi":"10.1609/aaai.v29i1.9445","title":"Solving Games with Functional Regret Estimation","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures; Office of Naval Research; Multidisciplinary University Research Initiative; Compute Canada","keywords":"Regret; Abstraction; Generalization; Computer science; Function (biology); Nash equilibrium; Corollary; Mathematical optimization; Sequence (biology); Theoretical computer science; Artificial intelligence; Machine learning; Mathematics; Discrete mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007943491,0.000301877,0.0002951482,0.0001888006,0.0002270471,0.000433166,0.001958518,0.0001100085,0.00005764908],"category_scores_gemma":[0.0009267224,0.000207795,0.000101016,0.0009759618,0.000507369,0.001115624,0.00039476,0.0003601328,0.0002357592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109444,"about_ca_system_score_gemma":0.0003204467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005974764,"about_ca_topic_score_gemma":0.00002234931,"domain_scores_codex":[0.9972115,0.00002712548,0.0006348621,0.0006300375,0.001060469,0.0004359764],"domain_scores_gemma":[0.9971346,0.000142055,0.0005178938,0.0004607446,0.00155681,0.000187873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001176994,0.0001229682,0.0004488339,0.00001834681,0.00001842244,0.000001083024,0.002089364,0.00251728,0.004053409,0.901123,0.0007907369,0.08869884],"study_design_scores_gemma":[0.00002574672,0.0003555768,0.000172796,0.0002281556,0.00001376263,0.00002034445,0.001253607,0.3079548,0.3958189,0.2937091,0.0001579336,0.0002893217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1677564,0.00006097972,0.7820814,0.01095676,0.001372812,0.0008638256,0.000004895554,0.0004445658,0.03645835],"genre_scores_gemma":[0.9757278,0.000008223486,0.02342536,0.0002349981,0.000100454,0.00003916122,7.089247e-7,0.00001828555,0.0004450295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8079714,"threshold_uncertainty_score":0.8473634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.125374786144741,"score_gpt":0.2995915743259147,"score_spread":0.1742167881811736,"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."}}