Roman Buckle is an PhD student in the Department of the Built Environment at the National University of Singapore (NUS), his research focuses on latent space exploration and synthetic data generation to improve the robustness and reliability of reinforcement learning control agents. His work also investigates how domain adaptation can enable transfer learning across buildings, and how explainable AI (XAI) can build operator trust in AI-driven controls, bridging advanced machine learning methods with real-world building operations.