Daniel Furelos-Blanco

Machine Learning Intern @ Epic Games.

I am a Machine Learning Intern at Epic Games, working on the use of foundation models to improve and create new gameplay experiences. I hold a Ph.D. in Computing from Imperial College London, where my research focused on reinforcement learning (RL) agents that can learn and exploit structured task representations in the form of finite-state machines, including work on their hierarchical composition. During my PhD, I also interned at InstaDeep, working on RL for combinatorial optimization.

After my PhD, I was a Research Associate at Imperial College London, where I continued working on finite-state machine task representations for RL — exploring new directions including autocurricula for training generalizable agents, first-order logic task representations, and learning representations from noisy observations — and co-supervised PhD and MSc students before joining Epic Games.

Selected Publications

  1. AAAI
    Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
    Daniel Furelos-Blanco, Charles Pert, Frederik Kelbel, Alex F. Spies, Alessandra Russo, and Michael Dennis
    AAAI Conference on Artificial Intelligence (AAAI), 2026
  2. ICML
    Hierarchies of Reward Machines
    Daniel Furelos-Blanco, Mark Law, Anders Jonsson, Krysia Broda, and Alessandra Russo
    International Conference on Machine Learning (ICML), 2023
  3. NeurIPS
    Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
    Nathan Grinsztajn, Daniel Furelos-Blanco, Shikha Surana, Clément Bonnet, and Thomas D. Barrett
    Neural Information Processing Systems (NeurIPS), 2023
  4. JAIR
    Induction and Exploitation of Subgoal Automata for Reinforcement Learning
    Daniel Furelos-Blanco, Mark Law, Anders Jonsson, Krysia Broda, and Alessandra Russo
    Journal of Artificial Intelligence Research (JAIR), 2021