Safe multi-agent reinforcement learning for wireless applications against adversarial communications
Based on the network observations and learning parameters shared by the neighboring
learning agents, multi-agent reinforcement learning (RL) has to enhance the performance …
learning agents, multi-agent reinforcement learning (RL) has to enhance the performance …
[PDF][PDF] Poisoning the well: can we simultaneously attack a group of learning agents?
ABSTRACT As Reinforcement Learning (RL) solutions are becoming ubiquitous, so is the
study of potential threats to their training and deployment. While single-learner training-time …
study of potential threats to their training and deployment. While single-learner training-time …
Optimal Cost Constrained Adversarial Attacks for Multiple Agent Systems
Since many security-related applications use multi-agent reinforcement learning as their
underlying algorithms, the study on the adversarial attacks against mutli-agent reinforcement …
underlying algorithms, the study on the adversarial attacks against mutli-agent reinforcement …
Multi-Agent Reinforcement Learning for Wireless Networks Against Adversarial Communications
Based on the efficient and reliable exchange of learning messages containing both the
policy selection experiences such as the learning parameters and observations among the …
policy selection experiences such as the learning parameters and observations among the …