{"id":"W4404799659","doi":"10.1016/j.neucom.2024.129005","title":"Enhancing cooperative multi-agent reinforcement learning through the integration of R-STDP and federated learning","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Telefonaktiebolaget LM Ericsson","keywords":"Reinforcement learning; Computer science; Reinforcement; Cooperative learning; Artificial intelligence; Machine learning; Mathematics education; Teaching method; Mathematics; Materials science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006714683,0.000233736,0.0002596349,0.00007939977,0.0006017335,0.0007839387,0.000352374,0.00005887731,0.000004006341],"category_scores_gemma":[0.0003161109,0.0001724628,0.00007449533,0.0005360579,0.00005042868,0.0005055031,0.0003437383,0.000605765,0.00001941902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006827734,"about_ca_system_score_gemma":0.00007212046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000155291,"about_ca_topic_score_gemma":0.00001632028,"domain_scores_codex":[0.9977863,0.0004353167,0.0005806915,0.0005306278,0.0003307376,0.0003363423],"domain_scores_gemma":[0.9988228,0.0005357009,0.0002171482,0.0002014513,0.0001712579,0.00005162187],"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":[0.00001408577,0.00005046844,0.0002931324,0.0002468968,0.0001520196,0.00006508685,0.03051241,0.6218275,0.2404095,0.01676145,0.0001058459,0.08956168],"study_design_scores_gemma":[0.0003386175,0.00014189,0.0002534431,0.0003659669,0.00001375317,0.00002684438,0.001043684,0.9800761,0.01542486,0.00001276307,0.002143072,0.0001589848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04770761,0.0004612149,0.9495873,0.0003545122,0.000533983,0.0004536008,4.904218e-7,0.0003692823,0.0005320063],"genre_scores_gemma":[0.9956983,0.0000187519,0.003589308,0.0001172806,0.00009292246,0.00001999661,0.000007641487,0.00001988254,0.000435949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9479907,"threshold_uncertainty_score":0.7559539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0293026118774923,"score_gpt":0.2814269726272203,"score_spread":0.252124360749728,"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."}}