BARD-MARL combines policy-graph features and Bayesian trust statistics from a BayesG substrate to detect Byzantine agents in learned-communication MARL, reporting AUC-ROC values from 0.843 to 0.982 under various attacks in SUMO traffic grids.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BARD-MARL: Byzantine-Agent Detection for Learned Communication in Multi-Agent Reinforcement Learning
BARD-MARL combines policy-graph features and Bayesian trust statistics from a BayesG substrate to detect Byzantine agents in learned-communication MARL, reporting AUC-ROC values from 0.843 to 0.982 under various attacks in SUMO traffic grids.