IBAL framework constructs information-theoretic adversarial attacks on agent observations and actions to train MARL agents that remain robust to interaction disruptions and agent-missing scenarios.
Byzantine robust cooperative multi- agent reinforcement learning as a bayesian game.arXiv preprint arXiv:2305.12872, 2023a
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Proposes HAD-MFC framework that decouples upper-level vulnerable agent selection from lower-level adversarial policy learning in large-scale MARL using Fenchel-Rockafellar transform and MDP reformulation with provable optimality preservation.
Wolfpack attack framework disrupts MARL cooperation by targeting initial and assisting agents; WALL trains robust policies against it with reported experimental gains.
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.
citing papers explorer
-
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
IBAL framework constructs information-theoretic adversarial attacks on agent observations and actions to train MARL agents that remain robust to interaction disruptions and agent-missing scenarios.
-
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
Proposes HAD-MFC framework that decouples upper-level vulnerable agent selection from lower-level adversarial policy learning in large-scale MARL using Fenchel-Rockafellar transform and MDP reformulation with provable optimality preservation.
-
Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
Wolfpack attack framework disrupts MARL cooperation by targeting initial and assisting agents; WALL trains robust policies against it with reported experimental gains.
-
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.