{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002331496,0.0008877749,0.001662983,0.0004829623,0.0007262384,0.001060799,0.002168037,0.001567231,0.004194607],"category_scores_gemma":[0.006525401,0.0004724557,0.0006004148,0.0007877208,0.001486078,0.001901245,0.0022724,0.002415276,0.0009078801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175389,"about_ca_system_score_gemma":0.002229027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002586569,"about_ca_topic_score_gemma":0.002647846,"domain_scores_codex":[0.9987831,0.0004512396,0.00005147215,0.0002654227,0.0003207145,0.000128092],"domain_scores_gemma":[0.9974124,0.001565074,0.0002367911,0.0002872488,0.0003049387,0.0001935233],"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":[0.0001590353,0.0002390296,0.0005674714,0.00009451446,0.00004465134,0.00008063837,0.0001243728,0.7841656,0.001760412,0.1114047,0.002556118,0.09880351],"study_design_scores_gemma":[0.0000652434,0.00006301374,0.00004307984,0.00000612585,0.000005459143,0.00001568592,0.000008307386,0.9693522,0.0004363715,0.02937162,0.0006245764,0.000008269689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008103576,0.00005810401,0.9893568,0.0001673449,0.00002365828,0.00004508823,0.00001667188,0.0002047386,0.002024083],"genre_scores_gemma":[0.5637689,0.0002295175,0.426969,0.0002412059,0.00008746674,0.0004405469,0.0001386589,0.0001302745,0.007994421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004194607,"threshold_uncertainty_score":0.01403236,"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."}}