Daniele Reda
Email: redad dot 93 at gmail dot com

I'm a reinforcement learning researcher at Wayve where we apply machine learning to robotics control to make self-driving cars.

My research interests in AI include deep reinforcement learning and deep learning for self-improving models with minimum to no supervision.

I completed my B.Sc. and my M.Sc. at Polytechnic University of Turin. During this period I was granted a double degree scholarship to study for one year at Telecom ParisTech - Eurecom Research Center. I was a visiting researcher at Berkeley AI Research at UC Berkeley for 6 months where I did research for my master thesis with professor Ruzena Bajcsy.

CV | Google Scholar | Github | LinkedIn | Twitter

Publications
Learning to drive in a day
Alex Kendall, Jeffrey Hawke, David Janz, Przemyslaw Mazur, Daniele Reda, John-Mark Allen, Vinh-Dieu Lam, Alex Bewley, Amar Shah

arXiv | blog post | pdf

Abstract: We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.

Outreach
  • I enjoy taking pictures and sharing them on Instagram.
  • I (try to) blog on my interests. Mostly mountain climbing/hiking and AI.

Template: this and this