相关论文: CuDA2: An approach for Incorporating Traitor Agent…
Autonomous cyber and cyber-physical systems need to perform decision-making, learning, and control in unknown environments. Such decision-making can be sensitive to multiple factors, including modeling errors, changes in costs, and impacts…
Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based…
Intelligent transportation systems require connected and automated vehicles (CAVs) to conduct safe and efficient cooperation with human-driven vehicles (HVs) in complex real-world traffic environments. However, the inherent unpredictability…
Before taking actions in an environment with more than one intelligent agent, an autonomous agent may benefit from reasoning about the other agents and utilizing a notion of a guarantee or confidence about the behavior of the system. In…
Efficient exploration strategy is one of essential issues in cooperative multi-agent reinforcement learning (MARL) algorithms requiring complex coordination. In this study, we introduce a new exploration method with the strangeness that can…
Cooperative multi-agent learning plays a crucial role for developing effective strategies to achieve individual or shared objectives in multi-agent teams. In real-world settings, agents may face unexpected failures, such as a robot's leg…
Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and…
We introduce Threatened Markov Decision Processes (TMDPs) as an extension of the classical Markov Decision Process framework for Reinforcement Learning (RL). TMDPs allow suporting a decision maker against potential opponents in a RL…
Multi-Agent Reinforcement Learning (MARL) has shown great potential as an adaptive solution for addressing modern cybersecurity challenges. MARL enables decentralized, adaptive, and collaborative defense strategies and provides an automated…
We consider the problem of robust multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents, mainly those trained in a centralized way, can be brittle because they can adopt policies that…
Cooperative multi-agent reinforcement learning (MARL) for navigation enables agents to cooperate to achieve their navigation goals. Using emergent communication, agents learn a communication protocol to coordinate and share information that…
This paper presents a cooperative multi-agent deep reinforcement learning (MADRL) approach for unmmaned aerial vehicle (UAV)-aided mobile edge computing (MEC) networks. An UAV with computing capability can provide task offlaoding services…
We study robustness to agent malfunctions in cooperative multi-agent reinforcement learning (MARL), a failure mode that is critical in practice yet underexplored in existing theory. We introduce MARTA, a plug-and-play robustness layer that…
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML…
In standard Reinforcement Learning (RL) settings, the interaction between the agent and the environment is typically modeled as a Markov Decision Process (MDP), which assumes that the agent observes the system state instantaneously, selects…
This paper considers the multi-agent reinforcement learning (MARL) problem for a networked (peer-to-peer) system in the presence of Byzantine agents. We build on an existing distributed $Q$-learning algorithm, and allow certain agents in…
Communication can promote coordination in cooperative Multi-Agent Reinforcement Learning (MARL). Nowadays, existing works mainly focus on improving the communication efficiency of agents, neglecting that real-world communication is much…
Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-modal settings and…
The dangers of adversarial attacks on Uncrewed Aerial Vehicle (UAV) agents operating in public are increasing. Adopting AI-based techniques and, more specifically, Deep Learning (DL) approaches to control and guide these UAVs can be…
Reinforcement learning agents are susceptible to evasion attacks during deployment. In single-agent environments, these attacks can occur through imperceptible perturbations injected into the inputs of the victim policy network. In…