3 papers
eess.SY2022
Cooperative Actor-Critic via TD Error Aggregation
Martin Figura, Yixuan Lin, Ji Liu +1
In decentralized cooperative multi-agent reinforcement learning, agents can aggregate information from one another to learn policies that maximize a team-average objective function…
cs.LG2021
Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation
Martin Figura, Yixuan Lin, Ji Liu +1
Adversarial attacks during training can strongly influence the performance of multi-agent reinforcement learning algorithms. It is, thus, highly desirable to augment existing algor…
eess.SY2021
Adversarial attacks in consensus-based multi-agent reinforcement learning
Martin Figura, Krishna Chaitanya Kosaraju, Vijay Gupta
Recently, many cooperative distributed multi-agent reinforcement learning (MARL) algorithms have been proposed in the literature. In this work, we study the effect of adversarial a…