PhD researcher · Research software developer

Reinforcement Learning, Planning and Research Software

PhD researcher at Coventry University and Research Software Developer at UCL, working on reinforcement learning, planning, reliable control and reproducible AI research software.

I develop learning and planning methods for energy-efficient building control, with a particular focus on Monte Carlo Tree Search, PPO and SAC. My research also studies interpretable policies and the numerical behaviour that can make reinforcement learning unreliable. At UCL, I build reproducible experimental software for multi-agent LLM research.