Related papers: Evolving intrinsic motivations for altruistic beha…

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…

Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented…

Reinforcement learning algorithms can train agents that solve problems in complex, interesting environments. Normally, the complexity of the trained agent is closely related to the complexity of the environment. This suggests that a highly…

Understanding the origins of volunteerism and free-riding is crucial in collective action situations where a sufficient number of cooperators is necessary to achieve shared benefits, such as in vaccination campaigns and social change…

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…

Advances in artificial intelligence often stem from the development of new environments that abstract real-world situations into a form where research can be done conveniently. This paper contributes such an environment based on ideas…

Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a…

In recent years, diversity has emerged as a useful mechanism to enhance the efficiency of multi-agent reinforcement learning (MARL). However, existing methods predominantly focus on designing policies based on individual agent…

This paper serves to introduce the reader to the field of multi-agent reinforcement learning (MARL) and its intersection with methods from the study of causality. We highlight key challenges in MARL and discuss these in the context of how…

Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge is addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of…

The universe involves many independent co-learning agents as an ever-evolving part of our observed environment. Yet, in practice, Multi-Agent Reinforcement Learning (MARL) applications are typically constrained to small, homogeneous…

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,…

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…

Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…

The multi-agent setting is intricate and unpredictable since the behaviors of multiple agents influence one another. To address this environmental uncertainty, distributional reinforcement learning algorithms that incorporate uncertainty…

In hybrid populations where humans delegate strategic decision-making to autonomous agents, understanding when and how cooperative behaviors can emerge remains a key challenge. We study this problem in the context of energy load management:…

Many real-life scenarios require humans to make difficult trade-offs: do we always follow all the traffic rules or do we violate the speed limit in an emergency? These scenarios force us to evaluate the trade-off between collective rules…

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. However, current methods pay little attention to the…

Many emerging agentic paradigms require agents to collaborate with one another (or people) to achieve shared goals. Unfortunately, existing approaches to learning policies for such collaborative problems produce brittle solutions that fail…