Robotics
Robot arm imitation learning
A simulated MuJoCo arm learns pick-and-place from demonstrations. Controlled runs compare behaviour cloning with my own ACT to find which part does the work.
99.0 %
success on unseen layouts, mean of three seedsPlain MLP 0.1 %
Limitation An MLP with chunking and ensembling reaches 87.3 %, so most of the gain doesn't come from the transformer.