Related papers: Compositional Learning for Modular Multi-Agent Sel…
We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to…
We introduce Compartmentalized Diffusion Models (CDM), a method to train different diffusion models (or prompts) on distinct data sources and arbitrarily compose them at inference time. The individual models can be trained in isolation, at…
Development of autonomous cyber system defense strategies and action recommendations in the real-world is challenging, and includes characterizing system state uncertainties and attack-defense dynamics. We propose a data-driven deep…
Efficient task scheduling in large-scale distributed systems presents significant challenges due to dynamic workloads, heterogeneous resources, and competing quality-of-service requirements. Traditional centralized approaches face…
Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually,…
Decentralized Multi-agent Learning (DML) enables collaborative model training while preserving data privacy. However, inherent heterogeneity in agents' resources (computation, communication, and task size) may lead to substantial variations…
This paper focuses on energy savings in downlink operation of cell-free massive MIMO (CF mMIMO) networks under dynamic traffic conditions. We propose a multi-agent deep reinforcement learning (MADRL) algorithm that enables each access point…
Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries…
Compositionality is a key strategy for addressing combinatorial complexity and the curse of dimensionality. Recent work has shown that compositional solutions can be learned and offer substantial gains across a variety of domains, including…
This paper presents a novel compositional approach to distributed coordination module (CM) synthesis for multiple discrete-event agents in the formal languages and automata framework. The approach is supported by two original ideas. The…
Since the advent of autonomous driving technology, it has experienced remarkable progress over the last decade. However, most existing research still struggles to address the challenges posed by environments where multiple vehicles have to…
In healthcare, multi-organ system diseases pose unique and significant challenges as they impact multiple physiological systems concurrently, demanding complex and coordinated treatment strategies. Despite recent advancements in the AI…
The Maximal Covering Location-Interdiction Problem (MCLIP) is a classic bi-level optimization problem, which is fundamental to resilient infrastructure planning yet remains computationally intractable. Specifically, the upper level…
In multi-agent informative path planning (MAIPP), agents must collectively construct a global belief map of an underlying distribution of interest (e.g., gas concentration, light intensity, or pollution levels) over a given domain, based on…
Recently, a deep reinforcement learning method is proposed to solve multiobjective optimization problem. In this method, the multiobjective optimization problem is decomposed to a number of single-objective optimization subproblems and all…
Reinforcement learning techniques are being explored as solutions to the threat of cyber attacks on enterprise networks. Recent research in the field of AI in cyber security has investigated the ability of homogeneous multi-agent…
This paper proposes a data-driven distributed voltage control approach based on the spectrum clustering and the enhanced multi-agent deep reinforcement learning (MADRL) algorithm. Via the unsupervised clustering, the whole distribution…
This paper proposes a novel centralized training and distributed execution (CTDE)-based multi-agent deep reinforcement learning (MADRL) method for multiple unmanned aerial vehicles (UAVs) control in autonomous mobile access applications.…
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…
Deep Reinforcement Learning (DRL) has recently witnessed significant advances that have led to multiple successes in solving sequential decision-making problems in various domains, particularly in wireless communications. The future…