Michael Matthews

Michael Matthews

Machine Learning Researcher

VivaCity

Biography

I am a Machine Learning Researcher on the Reinforcement Learning team at VivaCity, where I work on using RL for traffic control.

I completed my MSc in Machine Learning at University College London, where I worked on transfer learning in RL with UCL DARK Lab under the supervision of Tim Rocktäschel and Edward Grefenstette. Before this, I obtained my BA in Computer Science from the University of Cambridge, where I worked on data visualisation under the supervision of Damon Wischik.

I have previously completed software engineering internships at G-Research and PlayFusion, where I worked on internal trading software and RL for video games.

Interests
  • Deep Reinforcement Learning
  • Open-Ended Learning
  • Evolutionary Algorithms
Education
  • MSc in Machine Learning, 2021

    University College London

  • BA in Computer Science, 2020

    University of Cambridge

Publications

(2022). Multi-modal fusion by meta-initialization. arXiv preprint.

PDF Cite

(2022). Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning. In Conference on Lifelong Learning Agents 2022.

PDF Cite

(2022). SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning. ICLR Workshop on Agent Learning in Open-Endedness.

PDF Cite