Resilient adaptive optimal control of distributed multi-agent systems using reinforcement learning
Document Type
Article
Publication Date
11-6-2018
Department
Electrical Engineering
Abstract
This study presents a unified resilient model-free reinforcement learning (RL) based distributed control protocol for leader-follower multi-agent systems. Although RL has been successfully used to learn optimal control protocols for multi-agent systems, the effects of adversarial inputs are ignored. It is shown in this study, however, that their adverse effects can propagate across the network and impact the learning outcome of other intact agents. To alleviate this problem, a unified RL-based distributed control frameworks is developed for both homogeneous and heterogeneous multi-agent systems to prevent corrupted sensory data from propagating across the network. To this end, only the leader communicates its actual sensory information and other agents estimate the leader' state using a distributed observer and communicate this estimation to their neighbours to achieve consensus on the leader state. The observer cannot be physically affected by any adversarial input. To further improve resiliency, distributed H∞ control protocols are designed to attenuate the effect of the adversarial inputs on the compromised agent itself. An off-policy RL algorithm is developed to learn the solutions of the game algebraic Riccati equations arising from solving the H∞ control problem. No knowledge of the agent's dynamics is required and it is shown that the proposed RL-based H∞ control protocol is resilient against adversarial inputs. © The Institution of Engineering and Technology 2018.
DOI
10.1049/iet-cta.2018.0029
First Page
2165
Last Page
2174
Publication Title
IET Control Theory and Applications
Recommended Citation
Moghadam, R. and Modares, H. (2018). Resilient adaptive optimal control of distributed multi-agent systems using reinforcement learning. IET Control Theory Appl., 12: 2165-2174. https://doi.org/10.1049/iet-cta.2018.0029
Comments
At the time of publication, Rohollah Modhadam was affiliated with Missouri University of Science and Technology.