Research
Research in the group focuses on the areas described below. For more details about our research, see People and Publications.
Autonomous Agents and Multi-Agent Systems
Our long-term goal is to create autonomous agents that can accomplish tasks in complex environments, including multi-agent systems in which multiple agents must coordinate their actions in a shared environment. We develop algorithms enabling agents to reason about the actions, beliefs, and intentions of other agents from limited observations, combining such inferences with reinforcement learning and planning for effective decision making. We leverage foundation models to equip agents with richer reasoning capabilities, allowing them to interpret context and interact robustly with previously unseen partners.
Recent publications:
From Autonomy to Alliance: Robotic Foundation Models Must Learn With Us, Not Just For Us
A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning
Agent Modelling under Partial Observability for Deep Reinforcement Learning
Reinforcement Learning for Autonomous Systems
Reinforcement learning is a machine learning approach to solve sequential decision-making problems by interacting with the environment and learning from observations. Our research develops new approaches for efficient reinforcement learning with limited environment interactions, addressing core challenges such as sparse rewards, complex action spaces, partial observability, and robust generalisation to new environments. For multi-agent systems, we focus on learning optimal coordination strategies for multiple autonomous agents, including in agentic AI using large language models and embodied AI using vision-language-action models.
Recent publications:
NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
Applied AI and Industry Collaborations
We collaborate with industry partners to develop real-world applications of AI, tackling the challenges that arise when autonomous systems must operate reliably in complex, dynamic, and safety-critical environments. Our applied work includes motion planning and prediction for autonomous driving, scalable coordination for multi-robot warehouses, and human-AI workflow orchestration. A central challenge across these applications is bridging the gap between controlled research settings and the messiness of real deployments, where systems must handle rare events, incomplete information, and strict operational constraints.
Recent publications:
Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge
Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers
Interpretable Goal-based Prediction and Planning for Autonomous Driving