Related papers: Mis-spoke or mis-lead: Achieving Robustness in Mul…

Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has received immense interest in recent times and success manifests…

The growing prevalence of artificial intelligence (AI) in various applications underscores the need for agents that can successfully navigate and adapt to an ever-changing, open-ended world. A key challenge is ensuring these AI agents are…

Scalability is the key roadstone towards the application of cooperative intelligent algorithms in large-scale networks. Reinforcement learning (RL) is known as model-free and high efficient intelligent algorithm for communication problems…

This paper introduces Adversarial Resilience Learning (ARL), a concept to model, train, and analyze artificial neural networks as representations of competitive agents in highly complex systems. In our examples, the agents normally take the…

Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation, we propose the Wolfpack Adversarial Attack framework,…

Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and has made progress in various fields. Specifically, cooperative MARL focuses on training a team of agents to cooperatively achieve tasks that are…

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…

Recent advancements in deep learning techniques have opened new possibilities for designing solutions for autonomous cyber defence. Teams of intelligent agents in computer network defence roles may reveal promising avenues to safeguard…

As the applications of deep reinforcement learning (DRL) in wireless communications grow, sensitivity of DRL based wireless communication strategies against adversarial attacks has started to draw increasing attention. In order to address…

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…

In this letter, we propose a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework for Medium Access Control (MAC) protocol design. Unlike centralized approaches, which rely on a single entity for decision-making, MADRL empowers…

Explicit communication among humans is key to coordinating and learning. Social learning, which uses cues from experts, can greatly benefit from the usage of explicit communication to align heterogeneous policies, reduce sample complexity,…

We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…

We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This…

Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theoretically, adversarial perturbation in untargeted attacks can…

Multi-agent RL is rendered difficult due to the non-stationary nature of environment perceived by individual agents. Theoretically sound methods using the REINFORCE estimator are impeded by its high-variance, whereas value-function based…

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We…

In multi-agent reinforcement learning (MARL), effective communication improves agent performance, particularly under partial observability. We propose MARL-CPC, a framework that enables communication among fully decentralized, independent…

Autonomous cars are well known for being vulnerable to adversarial attacks that can compromise the safety of the car and pose danger to other road users. To effectively defend against adversaries, it is required to not only test autonomous…

Recent research studies revealed that neural networks are vulnerable to adversarial attacks. State-of-the-art defensive techniques add various adversarial examples in training to improve models' adversarial robustness. However, these…