Task-Agnostic Continual Reinforcement Learning: In Praise of a Simple Baseline
Date:
I was invited to Numenta’s reading group to give a talk on my recent task agnostic continual RL work.
Optimass
PhD student at MILA. Currently focusing on continual, transfer and meta-learning. On the job market!
- Montréal, QC, Canada
- Github
- Google Scholar