Related papers: Multi-Agent Actor-Critics in Autonomous Cyber Defe…

Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents. Enabling this development requires a…

Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper,…

Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions, leading to convoluted network structures. Building on the…

Multi-agent deep learning (MADL), including multi-agent deep reinforcement learning (MADRL), distributed/federated training, and graph-structured neural networks, is becoming a unifying framework for decision-making and inference in…

Recent technological progress in the development of Unmanned Aerial Vehicles (UAVs) together with decreasing acquisition costs make the application of drone fleets attractive for a wide variety of tasks. In agriculture, disaster management,…

In cooperative multi-agent reinforcement learning (c-MARL), agents learn to cooperatively take actions as a team to maximize a total team reward. We analyze the robustness of c-MARL to adversaries capable of attacking one of the agents on a…

When reward functions are hand-designed, deep reinforcement learning algorithms often suffer from reward misspecification, causing them to learn suboptimal policies in terms of the intended task objectives. In the single-agent case, inverse…

Developing effective Multi-Agent Systems (MAS) is critical for many applications requiring collaboration and coordination with humans. Despite the rapid advance of Multi-Agent Deep Reinforcement Learning (MADRL) in cooperative MAS, one…

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…

Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is increasingly essential for a range of interactive applications, such as industrial automation, self-driving vehicles, and augmented reality. However,…

In heterogeneous networks (HetNets), the overlap of small cells and the macro cell causes severe cross-tier interference. Although there exist some approaches to address this problem, they usually require global channel state information,…

Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework, deep reinforcement…

Multi-agent reinforcement learning (MARL) studies crucial principles that are applicable to a variety of fields, including wireless networking and autonomous driving. We propose a photonic-based decision-making algorithm to address one of…

The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group…

Mapping deep neural networks (DNNs) to hardware is critical for optimizing latency, energy consumption, and resource utilization, making it a cornerstone of high-performance accelerator design. Due to the vast and complex mapping space,…

Reinforcement learning (RL) enables agents to learn optimal behaviors through interaction with their environment and has been increasingly deployed in safety-critical applications, including autonomous driving. Despite its promise, RL is…

Financial systems run nonstop and must stay reliable even during cyber incidents. Modern attacks move across many services (apps, APIs, identity, payment rails), so defenders must make a sequence of actions under time pressure. Most…

The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that…

The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managing the vast influx of data from these platforms poses a…

Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (AI) agents to achieve robustness and generalization.…