Supervision via Competition: Robot Adversaries for Learning Tasks

Understand

There has been a recent paradigm shift in robotics to data-driven learning for planning and control.

• Due to large number of experiences required for training, most of these approaches use a self-supervised paradigm: using sensors to measure success/failure.
• However, in most cases, these sensors provide weak supervision at best.
• In this work, we propose an adversarial learning framework that pits an adversary against the robot learning the task.