{"id":"W4412081721","doi":"10.1109/tnse.2025.3586602","title":"Non-Cooperative Multi-Agent Reinforcement Learning Exploiting Population Dynamics","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Mathematical and Theoretical Epidemiology and Ecology Models","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Population; Multi-agent system; Dynamics (music); Artificial intelligence; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005634357,0.00009118827,0.0001757398,0.00009435113,0.0003705919,0.00001321144,0.00004008189,0.00006455305,0.00002161717],"category_scores_gemma":[0.00006068706,0.00007446679,0.00003114346,0.0003267586,0.000116817,0.0000857384,0.000002514023,0.0002661519,0.000004535963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008937266,"about_ca_system_score_gemma":0.00003069077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007036696,"about_ca_topic_score_gemma":0.00000320296,"domain_scores_codex":[0.99928,0.000009005368,0.0001844489,0.0001823414,0.00008662692,0.000257587],"domain_scores_gemma":[0.999649,0.000123301,0.00001791653,0.00007676607,0.00004786209,0.00008516449],"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":[0.00001827818,0.00002421449,0.0001860098,0.00003942246,0.00001664772,0.00000147835,0.00007392959,0.9729921,0.0002024064,0.02342815,0.000004398953,0.003012992],"study_design_scores_gemma":[0.000244451,0.00008302446,0.001266181,0.0001917944,0.00003004205,0.000004748462,0.00005726156,0.9975412,0.0003169084,0.0001844667,0.00001343568,0.00006649661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1073362,0.00001428558,0.8911486,0.0002448711,0.0002255403,0.0001347613,1.558667e-7,0.00004659756,0.0008489231],"genre_scores_gemma":[0.9967902,0.00004413355,0.002439625,0.000267612,0.0000222628,0.00002738675,0.00000118667,0.000004200149,0.0004034123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8894539,"threshold_uncertainty_score":0.3036668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01687148021500613,"score_gpt":0.2711063532501886,"score_spread":0.2542348730351824,"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."}}