多智能体系统

Game-based decision-making involves reasoning over both world dynamics and strategic interactions among the agents. Typically, empirical models capturing these respective aspects are learned and used separately. We investigate the potential…

Cooperative Multi-agent Reinforcement Learning (MARL) has attracted significant attention and played the potential for many real-world applications. Previous arts mainly focus on facilitating the coordination ability from different aspects…

I propose a novel Ising-like model of language evolution. In a simple way, Ising-like models represent the countervailing tendencies towards convergence and change present in language evolution. In the ordinary Ising-model, a node on a…

Learning communication strategies in cooperative multi-agent reinforcement learning (MARL) has recently attracted intensive attention. Early studies typically assumed a fully-connected communication topology among agents, which induces high…

The iterated learning model is an agent-based model of language evolution notable for demonstrating the emergence of compositional language. In its original form, it modelled language evolution along a single chain of teacher-pupil…

Offloading computation to nearby edge/fog computing nodes, including the ones carried by moving vehicles, e.g., vehicular fog nodes (VFN), has proved to be a promising approach for enabling low-latency and compute-intensive mobility…

In this short position paper we highlight our ongoing work on verifiable heterogeneous multi-agent systems and, in particular, the complex (and often non-functional) issues that impact the choice of structure within each agent.

Multi-robot navigation is the task of finding trajectories for a team of robotic agents to reach their destinations as quickly as possible without collisions. In this work, we introduce a new problem: fair-delay multi-robot navigation,…

Collaboration in multi-agent autonomous systems is critical to increase performance while ensuring safety. However, due to heterogeneity of their features in, e.g., perception qualities, some autonomous systems have to be considered more…

In this article, we focus on the cooperative state estimation problem of a multi-agent system. Each agent is equipped with absolute and relative measurements. The purpose of this research is to make each agent generate its own state…

We consider the problem of synthesizing resilient and stochastically stable strategies for systems of cooperating agents striving to minimize the expected time between consecutive visits to selected locations in a known environment. A…

Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their…

Citizen-focused democratic processes where participants deliberate on alternatives and then vote to make the final decision are increasingly popular today. While the computational social choice literature has extensively investigated voting…

Several distributed algorithms are presented for the exploration of unknown indoor regions by a swarm of flying, energy constrained agents. The agents, which are identical, autonomous, anonymous and oblivious, uniformly cover the region and…

This paper considers multi-agent reinforcement learning (MARL) where the rewards are received after delays and the delay time varies across agents and across time steps. Based on the V-learning framework, this paper proposes MARL algorithms…

We explore space traffic management as an application of collision-free navigation in multi-agent systems where vehicles have limited observation and communication ranges. We investigate the effectiveness of transferring a collision…

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which…

We propose a type of non-cooperative game, termed multi-cluster aggregative game, which is composed of clusters as players, where each cluster consists of collaborative agents with cost functions depending on their own decisions and the…

Some standardized environments have been designed for partially observable multi-agent cooperation, but we find most current environments are synchronous, whereas real-world agents often have their own action spaces leading to asynchrony.…

Consider a given planar circular region, in which there is an unknown number of smart mobile evaders. We wish to detect evaders using a line formation of sweeping agents whose total sensing length is predetermined. We propose procedures for…