Multi-Task Federated Reinforcement Learning with Adversaries
This addresses security vulnerabilities in collaborative reinforcement learning systems, but it is incremental as it builds on existing federated and adversarial learning frameworks.
The paper tackles the problem of adversarial attacks in multi-task federated reinforcement learning, proposing an adaptive attack method that outperforms general attacks and a modified algorithm that achieves near-optimal policies in adversarial settings.
Reinforcement learning algorithms, just like any other Machine learning algorithm pose a serious threat from adversaries. The adversaries can manipulate the learning algorithm resulting in non-optimal policies. In this paper, we analyze the Multi-task Federated Reinforcement Learning algorithms, where multiple collaborative agents in various environments are trying to maximize the sum of discounted return, in the presence of adversarial agents. We argue that the common attack methods are not guaranteed to carry out a successful attack on Multi-task Federated Reinforcement Learning and propose an adaptive attack method with better attack performance. Furthermore, we modify the conventional federated reinforcement learning algorithm to address the issue of adversaries that works equally well with and without the adversaries. Experimentation on different small to mid-size reinforcement learning problems show that the proposed attack method outperforms other general attack methods and the proposed modification to federated reinforcement learning algorithm was able to achieve near-optimal policies in the presence of adversarial agents.