Related papers: Generalising Multi-Agent Cooperation through Task-…

Large language model (LLM) agents struggle to autonomously evolve coordination strategies in dynamic environments, largely because coarse global outcomes obscure the causal signals needed for local policy refinement. We identify this…

This paper explores the impact of relational state abstraction on sample efficiency and performance in collaborative Multi-Agent Reinforcement Learning. The proposed abstraction is based on spatial relationships in environments where direct…

We study multi-agent reinforcement learning (MARL) with centralized training and decentralized execution. During the training, new agents may join, and existing agents may unexpectedly leave the training. In such situations, a standard deep…

Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems,…

In the real world, people/entities usually find matches independently and autonomously, such as finding jobs, partners, roommates, etc. It is possible that this search for matches starts with no initial knowledge of the environment. We…

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

Computational models of emergent communication in agent populations are currently gaining interest in the machine learning community due to recent advances in Multi-Agent Reinforcement Learning (MARL). Current contributions are however…

Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL). Most previous work uses continuous message communication whose high representational capacity comes at the expense of…

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Centralized training with decentralized execution (CTDE) is a widely-used learning paradigm that has achieved significant success in complex tasks. However, partial observability issues and the absence of effectively shared signals between…

Communication enables coordination in multi-agent reinforcement learning (MARL), but many real-world applications, e.g., search-and-rescue with drone swarms, operate under severe bandwidth constraints. Many communication architectures still…

This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL literature, which are…

Multi-agent reinforcement learning (MARL) methods typically require that agents enjoy global state observability, preventing development of decentralized algorithms and limiting scalability. Recent work has shown that, under assumptions on…

Mission-oriented drone networks have been widely used for structural inspection, disaster monitoring, border surveillance, etc. Due to the limited battery capacity of drones, mission execution strategy impacts network performance and…

Multi-Agent Reinforcement Learning (MARL) provides a powerful framework for learning coordination in multi-agent systems. However, applying MARL to robotics still remains challenging due to high-dimensional continuous joint action spaces,…

The exploration of unknown, Global Navigation Satellite System (GNSS) denied environments by an autonomous communication-aware and collaborative group of Unmanned Aerial Vehicles (UAVs) presents significant challenges in coordination,…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

This paper aims to develop a paradigm that models the learning behavior of intelligent agents (including but not limited to autonomous vehicles, connected and automated vehicles, or human-driven vehicles with intelligent navigation systems…

Training agents that can coordinate zero-shot with humans is a key mission in multi-agent reinforcement learning (MARL). Current algorithms focus on training simulated human partner policies which are then used to train a Cooperator agent.…

Cooperative multi-agent reinforcement learning (MARL) aims to develop agents that can collaborate effectively. However, most cooperative MARL methods overfit training agents, making learned policies not generalize well to unseen…