8 papers
Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge
Charlie Masters, Advaith Vellanki, Jiangbo Shangguan +4
While agentic AI has advanced in automating individual tasks, managing complex multi-agent workflows remains a challenging problem. This paper presents a research vision for autono…
Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour
Bálint Gyevnár, Christopher G. Lucas, Stefano V. Albrecht +1
Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is v…
Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning
Samuel Garcin, Trevor McInroe, Pablo Samuel Castro +4
Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further co…
HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
Kale-ab Abebe Tessera, Arrasy Rahman, Amos Storkey +1
Adaptive cooperation in multi-agent reinforcement learning (MARL) requires policies to express homogeneous, specialised, or mixed behaviours, yet achieving this adaptivity remains…
Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning
Xuehui Yu, Mhairi Dunion, Xin Li +1
Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes o…
Multi-Agent Reinforcement Learning for Energy Networks: Computational Challenges, Progress and Open Problems
Sarah Keren, Chaimaa Essayeh, Stefano V. Albrecht +1
The rapidly changing architecture and functionality of electrical networks and the increasing penetration of renewable and distributed energy resources have resulted in various tec…
DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design
Samuel Garcin, James Doran, Shangmin Guo +2
Autonomous agents trained using deep reinforcement learning (RL) often lack the ability to successfully generalise to new environments, even when these environments share character…
How the level sampling process impacts zero-shot generalisation in deep reinforcement learning
Samuel Garcin, James Doran, Shangmin Guo +2
A key limitation preventing the wider adoption of autonomous agents trained via deep reinforcement learning (RL) is their limited ability to generalise to new environments, even wh…