{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001366948,0.0007148403,0.0009951305,0.0003817909,0.0004927983,0.0007414077,0.001575879,0.0008509625,0.0009503505],"category_scores_gemma":[0.003759155,0.0003130954,0.0004043167,0.0003171518,0.000987942,0.0008277333,0.001194978,0.00103622,0.0001842629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008188421,"about_ca_system_score_gemma":0.001273565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005044703,"about_ca_topic_score_gemma":0.003502861,"domain_scores_codex":[0.9994985,0.0001812751,0.000020939,0.0001045258,0.0001110685,0.00008370607],"domain_scores_gemma":[0.9979134,0.001295667,0.0002630749,0.0001062397,0.0002897339,0.0001318001],"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":[0.00002529737,0.000040786,0.0007486873,0.0000225769,0.00002473513,0.00005310216,0.00003610291,0.9793576,0.0007695569,0.005675204,0.0002925054,0.0129538],"study_design_scores_gemma":[0.00000486761,0.00001093703,0.0000299402,0.000001055945,0.000001792648,0.000004623766,0.00000265854,0.9985933,0.00008769812,0.001194087,0.00006764497,0.000001340569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03665355,0.0001138202,0.9609106,0.0001679661,0.00002577718,0.00005742506,0.00001583119,0.0002095709,0.001845502],"genre_scores_gemma":[0.9420219,0.00007300264,0.05604996,0.0001239668,0.00001716896,0.0001366432,0.00003684018,0.00002532073,0.001515239],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005044703,"threshold_uncertainty_score":0.01003069,"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."}}