Evaluating Robustness of Cooperative MARL: A Model-based Approach

by   Nhan H. Pham, et al.
University of California, San Diego

In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial attacks has been rarely explored. In this paper, we propose to evaluate the robustness of c-MARL agents via a model-based approach. Our proposed formulation can craft stronger adversarial state perturbations of c-MARL agents(s) to lower total team rewards more than existing model-free approaches. In addition, we propose the first victim-agent selection strategy which allows us to develop even stronger adversarial attack. Numerical experiments on multi-agent MuJoCo benchmarks illustrate the advantage of our approach over other baselines. The proposed model-based attack consistently outperforms other baselines in all tested environments.


page 2

page 12

page 13


Sparse Adversarial Attack in Multi-agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (cMARL) has many real app...

On the Robustness of Cooperative Multi-Agent Reinforcement Learning

In cooperative multi-agent reinforcement learning (c-MARL), agents learn...

Decentralized Adversarial Training over Graphs

The vulnerability of machine learning models to adversarial attacks has ...

Model-Based Stochastic Search for Large Scale Optimization of Multi-Agent UAV Swarms

Recent work from the reinforcement learning community has shown that Evo...

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning

While deep neural networks (DNNs) have strengthened the performance of c...

Multi-Agent Adversarial Training Using Diffusion Learning

This work focuses on adversarial learning over graphs. We propose a gene...

Learning cooperative behaviours in adversarial multi-agent systems

This work extends an existing virtual multi-agent platform called RoboSu...

Please sign up or login with your details

Forgot password? Click here to reset