Resilient Consensus-based Multi-agent Reinforcement Learning

by   Martin Figura, et al.

Adversarial attacks during training can strongly influence the performance of multi-agent reinforcement learning algorithms. It is, thus, highly desirable to augment existing algorithms such that the impact of adversarial attacks on cooperative networks is eliminated, or at least bounded. In this work, we consider a fully decentralized network, where each agent receives a local reward and observes the global state and action. We propose a resilient consensus-based actor-critic algorithm, whereby each agent estimates the team-average reward and value function, and communicates the associated parameter vectors to its immediate neighbors. We show that in the presence of Byzantine agents, whose estimation and communication strategies are completely arbitrary, the estimates of the cooperative agents converge to a bounded consensus value with probability one, provided that there are at most H Byzantine agents in the neighborhood of each cooperative agent and the network is (2H+1)-robust. Furthermore, we prove that the policy of the cooperative agents converges with probability one to a bounded neighborhood around a local maximizer of their team-average objective function under the assumption that the policies of the adversarial agents asymptotically become stationary.


Adversarial attacks in consensus-based multi-agent reinforcement learning

Recently, many cooperative distributed multi-agent reinforcement learnin...

Cooperative Actor-Critic via TD Error Aggregation

In decentralized cooperative multi-agent reinforcement learning, agents ...

Resilient Dynamic Average Consensus based on Trusted agents

In this paper, we address the discrete-time dynamic average consensus (D...

Resilient Consensus via Voronoi Communication Graphs

Consensus algorithms form the foundation for many distributed algorithms...

Reward-Reinforced Reinforcement Learning for Multi-agent Systems

Reinforcement learning algorithms in multi-agent systems deliver highly ...

Planning Not to Talk: Multiagent Systems that are Robust to Communication Loss

In a cooperative multiagent system, a collection of agents executes a jo...

Please sign up or login with your details

Forgot password? Click here to reset