1. 'Posterior Sampling for Deep Reinforcement Learning', International Conference on Machine Learning (ICML), 2023.
2. 'Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning', Transactions on Machine Learning Research (TMLR), 2023.
Research Experience
AI Developer at xDNA, working on tools for fact-checking (Project Aletheia) and large-scale object recognition.
Education
Ph.D. candidate at Queen Mary University of London, supervised by Paulo Rauber.
Background
Research interests: developing scalable and sample-efficient reinforcement learning algorithms, with a particular emphasis on Large Language Models, Vision Language Models, Bayesian methods, and model-based approaches.