Active gaze and sparse attention extensions for AME2 cut humanoid robot training costs to 20%
The methods improve navigation across diverse and difficult terrains.
Most Activity
i've been doing this myself. you can think of this as foveated rendering that VR headsets use. most of the time gets taken up rendering, but what you can do is actually just give the policy the ability to "direct the eye" and it learns really well in RL
Such a cool line of work
I've had policies learn interesting things like scanning behaviours without me explicitly having them learn it. Ray tracing is very batchable too. This was deployed to real
i've been doing this myself. you can think of this as foveated rendering that VR headsets use. most of the time gets taken up rendering, but what you can do is actually just give the policy the ability to "direct the eye" and it learns really well in RL
