Search Results for author:
Found 1 papers, 0 papers with code
SAFE-GIL: SAFEty Guided Imitation Learning
The algorithm abstracts the imitation error as an adversarial disturbance in the system dynamics, injects it during data collection to expose the expert to safety critical states, and collects corrective actions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
