A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning
This addresses the sample inefficiency problem in deep RL for robotics, enabling rapid real-world deployment without domain knowledge, though it is incremental in combining existing advancements.
The paper tackled learning quadruped locomotion in real-world environments using model-free reinforcement learning, achieving consistent walking gaits on challenging terrains in only 20 minutes.
Deep reinforcement learning is a promising approach to learning policies in uncontrolled environments that do not require domain knowledge. Unfortunately, due to sample inefficiency, deep RL applications have primarily focused on simulated environments. In this work, we demonstrate that the recent advancements in machine learning algorithms and libraries combined with a carefully tuned robot controller lead to learning quadruped locomotion in only 20 minutes in the real world. We evaluate our approach on several indoor and outdoor terrains which are known to be challenging for classical model-based controllers. We observe the robot to be able to learn walking gait consistently on all of these terrains. Finally, we evaluate our design decisions in a simulated environment.