Aidan Scannell

Postdoctoral researcher | Machine learning | Sequential decision making | Robotics

Biography

Hello, my name is Aidan Scannell and I am a postdoctoral researcher with interests at the intersection of machine learning, sequential decision making and robotics. My research aims at enabling autonomous agents to learn behaviours, such that they can learn to solve any task. I am particularly interested in robotics applications, the challenges associated with deploying lifelong agents, and equipping agents with the ability to know when they do not know.

Bio:

I am a Finnish Center for Artificial Intelligence postdoctoral researcher at Aalto University in Joni Pajarinen’s Robot Learning Lab and Arno Solin’s Machine Learning Research Group. I obtained my PhD from the University of Bristol under the supervision of Arthur Richards and Carl Henrik Ek. During my PhD I developed methods for controlling quadcopters in uncertain environments by synergising methods from probabilistic machine learning, stochastic differential geometry and reinforcement learning.

Interests
  • Reinforcement learning
  • Lifelong learning
  • World models
  • Probabilistic machine learning
  • Decision-making under unc.
  • Robotics
Education
  • PhD in Robotics and Autonomous Systems, 2022

    University of Bristol, UK

  • MEng Mechanical Engineering, 2016

    University of Bristol, UK

News

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). Function-space Prameterization of Neural Networks for Sequential Learning. The Twelth International Conference on Learning Representations (ICLR).

PDF Cite Code Website

(2023). Sparse Function-space Representation of Neural Networks. ICML 2023 Workshop on Duality Principles for Modern Machine Learning.

PDF Cite Code Poster Website

(2023). Mode-constrained Model-based Reinforcement Learning via Gaussian Processes. 26th International Conference on Artificial Intelligence and Statistics (AISTATS).

PDF Cite Code Project Poster Source Document Follow

(2021). Identifiable Mixtures of Sparse Variational Gaussian Process Experts. UK RAS CDT Conference.

PDF Code Project

Projects

.js-id-research

Contact