Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization

Understand

Training deep reinforcement learning (DRL) locomotion policies often require massive amounts of data to converge to the desired behaviour.

• In this regard, simulators provide a cheap and abundant source.
• For successful sim-to-real transfer, exhaustively engineered approaches such as system identification, dynamics randomization, and domain adaptation are generally employed.
• As an alternative, we investigate a simple strategy of random force injection (RFI) to perturb system dynamics during training.