Fault Tolerant Multi-Agent Learning with Adversarial Budget Constraints
Abstract
We study robustness to agent malfunctions in cooperative multi-agent reinforcement learning (MARL), a failure mode that is critical in practice yet underexplored in existing theory. We introduce MARTA, a plug-and-play robustness layer that augments standard MARL algorithms with a Switcher-Adversary mechanism which selectively induces malfunctions in performance-critical states. This formulation defines a fault-switching -player Markov game in which the Switcher chooses when and which agent fails, and the Adversary controls the resulting faulty behaviour via random or worst-case policies. We develop a Q-learning-type scheme and show that the associated Bellman operator is a contraction, yielding existence and uniqueness of the minimax value, convergence to a Markov perfect equilibrium. MARTA integrates seamlessly with MARL algorithms without architectural modification and consistently improves robustness across Traffic Junction (TJ), Level-Based Foraging (LBF), MPE SimpleTag, and SMAC (v2). In these domains, MARTA achieves large gains in final performance of up to 116.7\% in SMAC, 21.4\% in MPE SimpleTag, and 44.6\% in LBF, while significantly reducing failure rates under train-test mismatched fault regimes. These results establish MARTA as a theoretically grounded and practically deployable mechanism for fault-tolerant MARL.
Cite
@article{arxiv.2508.08800,
title = {Fault Tolerant Multi-Agent Learning with Adversarial Budget Constraints},
author = {David Mguni and Yaqi Sun and Haojun Chen and Wanrong Yang and Amir Darabi and Larry Olanrewaju Orimoloye and Yaodong Yang},
journal= {arXiv preprint arXiv:2508.08800},
year = {2026}
}