{"id":"W2180467047","doi":"10.1007/s10462-015-9447-5","title":"Exponential moving average based multiagent reinforcement learning algorithms","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Nash equilibrium; Computer science; Reinforcement learning; Algorithm; Convergence (economics); Q-learning; Weighted Majority Algorithm; Mathematical optimization; Artificial intelligence; Mathematics; Wake-sleep algorithm; Unsupervised learning; Generalization error","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001885558,0.000280401,0.0004180069,0.0001076776,0.0001805709,0.0002012646,0.001080574,0.0000628207,0.00007196194],"category_scores_gemma":[0.0008410765,0.0002610228,0.0002074195,0.0005713238,0.00007722726,0.0004870576,0.000336941,0.000321671,0.000792449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000204653,"about_ca_system_score_gemma":0.000222072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001022243,"about_ca_topic_score_gemma":0.000009547462,"domain_scores_codex":[0.9970272,0.000306409,0.0008104813,0.0006017138,0.0006847344,0.0005694792],"domain_scores_gemma":[0.9982266,0.0001498012,0.0002964796,0.00069485,0.0003147048,0.000317559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006657117,0.00006758144,0.00001104973,0.0001274136,0.0000197314,0.00004491833,0.0002503665,0.02860586,0.0001148116,0.01913219,0.00008666343,0.9515328],"study_design_scores_gemma":[0.00005453851,0.0001674712,0.000002925498,0.0007124033,0.00002405546,0.00000800097,0.00004233008,0.9756024,0.001770957,0.001291164,0.02000455,0.0003192128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00006333844,0.01015159,0.9866174,0.001172487,0.0005628252,0.000730596,4.482994e-7,0.0002902358,0.0004110359],"genre_scores_gemma":[0.8897086,0.002787557,0.1045224,0.002154686,0.0002536546,0.0002291533,0.00001972073,0.00003860888,0.000285653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9512135,"threshold_uncertainty_score":0.9999856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0888835926429212,"score_gpt":0.3256896554819136,"score_spread":0.2368060628389924,"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."}}