{"id":"W2152711271","doi":"10.1109/acc.2011.5990832","title":"Decentralized learning in two-player zero-sum games: A L<inf>R-I</inf> lagging anchor algorithm","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Lagging; Zero (linguistics); Algorithm; Action (physics); Computer science; Zero-sum game; Matrix (chemical analysis); Nash equilibrium; Artificial intelligence; Mathematics; Discrete mathematics; Mathematical optimization; Statistics; Physics; Philosophy","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":[0.001146692,0.0005647627,0.0006183231,0.0005236372,0.0002798123,0.0004589478,0.001832592,0.0001893029,0.0006724515],"category_scores_gemma":[0.000294215,0.0005399596,0.0002035934,0.001152724,0.0001194936,0.001415462,0.0007737912,0.0008435529,0.0007453297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002409998,"about_ca_system_score_gemma":0.0001779178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002178361,"about_ca_topic_score_gemma":0.00005495685,"domain_scores_codex":[0.9952269,0.0003179979,0.0009791482,0.001026213,0.0009170486,0.001532755],"domain_scores_gemma":[0.9976733,0.0002654094,0.0003953199,0.001112608,0.00018762,0.0003657363],"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":[0.0001180365,0.0005274345,0.05919249,0.0001587478,0.0003354084,0.0008058413,0.02264865,0.6368428,0.006943371,0.06740467,0.008341985,0.1966806],"study_design_scores_gemma":[0.002504537,0.0002302739,0.005152749,0.0001696157,0.00002478523,0.00005097678,0.0001358959,0.955119,0.001986881,0.0005215102,0.03319576,0.0009080011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01056151,0.0001968674,0.9586629,0.0001977407,0.0007981522,0.0004933067,7.968735e-7,0.00096386,0.02812483],"genre_scores_gemma":[0.545603,0.0002001152,0.4437943,0.0009724773,0.0001278884,0.00005812677,0.00001357169,0.00008730453,0.009143195],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5350415,"threshold_uncertainty_score":0.9997052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02508932199920117,"score_gpt":0.2615194800626202,"score_spread":0.236430158063419,"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."}}