2 papers
cs.CV2025
SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens
Alexandre Brown, Glen Berseth
Visual reinforcement learning policies trained on pixel observations often struggle to generalize when visual conditions change at test time. Object-centric representations are a p…
cs.LG2019
Towards Learning to Imitate from a Single Video Demonstration
Glen Berseth, Florian Golemo, Christopher Pal
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. Howeve…