Daniel Jarne Ornia
I am a researcher in AI for control. I obtained a PhD at Delft University of Technology (Delft Center for Systems and Control) working on swarm robotics, model free multi-agent systems and formal methods for RL. I am currently a postdoc researcher at the Cognitive Robotics Lab (TU Delft), working on risk-aware decision making for intelligent agents.

Personally, I spent most of my free time surfing, snowboarding or climbing, I enjoy playing music and I speak a bunch of languages1.

Research

I completed my PhD in Delft under the supervision of Dr Manuel Mazo in 2023. During these years I spent the summer of 2022 at the University of Oxford, working with Prof. Alessandro Abate on robust reinforcement learning problems. My research has ranged from mean field approximations for stochastic systems (paper) to communication-induced uncertainty in multi-agent RL (paper) and verifiable robustness in RL (paper).
Nowadays I am interested in problems related to decision making under uncertainty, safety and interpretability in RL, distributional RL and information theoretic control.

News

Footnotes

1 Spanish, English, Catalan, French, Dutch