no code implementations • 3 Jun 2024 • Pranav Agarwal, Sheldon Andrews, Samira Ebrahimi Kahou
We incorporate a transformer-decoder for auto-regressive world modeling and a transformer-encoder for learning behavior by attending to task-relevant cues in the discrete representation of the world model.
1 code implementation • 30 Sep 2023 • Pei Xu, Kaixiang Xie, Sheldon Andrews, Paul G. Kry, Michael Neff, Morgan McGuire, Ioannis Karamouzas, Victor Zordan
The technique is shown to be effective for adapting existing physics-based controllers to a wide range of new styles for locomotion, new task targets, changes in character morphology and extensive changes in environment.
1 code implementation • 15 Nov 2022 • Pranav Agarwal, Marek Teichmann, Sheldon Andrews, Samira Ebrahimi Kahou
Training novice users to operate an excavator for learning different skills requires the presence of expert teachers.