Related papers: Interpreting Agent Behaviors in Reinforcement-Lear…

This work presents a Hierarchical Multi-Agent Reinforcement Learning framework for analyzing simulated air combat scenarios involving heterogeneous agents. The objective is to identify effective Courses of Action that lead to mission…

The ability of modeling the other agents, such as understanding their intentions and skills, is essential to an agent's interactions with other agents. Conventional agent modeling relies on passive observation from demonstrations. In this…

This work focuses on the problem of distributed optimization in multi-agent cyberphysical systems, where a legitimate agent's iterates are influenced both by the values it receives from potentially malicious neighboring agents, and by its…

We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a…

Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and…

Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a…

One of the remaining challenges in reinforcement learning is to develop agents that can generalise to novel scenarios they might encounter once deployed. This challenge is often framed in a multi-task setting where agents train on a fixed…

Classical coding-theoretic guarantees often rely on trust assumptions, such as requiring sufficiently many honest nodes compared with adversarial ones. These assumptions are difficult to enforce in open decentralized systems where…

Animal vision is thought to optimize various objectives from metabolic efficiency to discrimination performance, yet its ultimate objective is to facilitate the survival of the animal within its ecological niche. However, modeling animal…

Both parasites in biological systems and adversarial forces in cybersecurity are often perceived as threats: disruptive elements that must be eliminated. However, these entities play a critical role in revealing systemic weaknesses, driving…

Continual learning is often motivated by the idea, known as the big world hypothesis, that "the world is bigger" than the agent. Recent problem formulations capture this idea by explicitly constraining an agent relative to the environment.…

Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…

Deception is rapidly growing as an important tool for cyber defence, complementing existing perimeter security measures to rapidly detect breaches and data theft. One of the factors limiting the use of deception has been the cost of…

For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated exploits requires deep expertise and manual effort, leading…

Although adverse effects of attacks have been acknowledged in many cyber-physical systems, there is no system-theoretic comprehension of how a compromised agent can leverage communication capabilities to maximize the damage in distributed…

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.…

Addressing complex cooperative tasks in safety-critical environments poses significant challenges for multi-agent systems, especially under conditions of partial observability. We focus on a dynamic network bridging task, where agents must…

This paper studies a strategic security problem in networked control systems under stealthy false data injection attacks. The security problem is modeled as a bilateral cognitive security game between a defender and an adversary, each…

Code protections aim at blocking (or at least delaying) reverse engineering and tampering attacks to critical assets within programs. Knowing the way hackers understand protected code and perform attacks is important to achieve a stronger…

We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment,…