Shimon Whiteson

Shimon Whiteson is Professor of Computer Science at the University of Oxford, leading the Whiteson Research Lab focused on reinforcement learning, multi-agent systems, and deep learning. His research develops algorithms for efficient learning in complex environments.

Current work explores meta-reinforcement learning frameworks that enable agents to rapidly adapt to new tasks, with applications in autonomous driving simulation and robotics. Recent innovations include novel methods for offline reinforcement learning, multi-agent coordination, and morphology-aware control.

Publications demonstrate advances in:

• Meta-RL algorithm design for few-shot adaptation
• Multi-agent reinforcement learning environments and benchmarks
• Imitation learning in autonomous driving
• Bayesian methods for sample-efficient learning

Research outputs include widely used benchmarks and tools including JaxMARL for accelerated multi-agent RL research. Current doctoral supervision focuses on temporal abstraction in RL, multi-agent coordination, and reinforcement learning theory.