Demonstrating A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning

Abstract

Fig. 1: We demonstrate that deep reinforcement learning can be used to efficiently train a quadruped robot directly on various real world terrains, e.g., flat ground (blue); soft, irregular mulch (green); grass (red); and a hiking trail (yellow), acquiring effective gaits within 20 minutes of training.Abstract-Deep reinforcement learning is a promising approach to learning policies in unstructured environments.Due to its sample inefficiency, though, 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 careful MDP formulation lead to learning quadruped locomotion in only 20 minutes in the real world.We evaluate our approach on several indoor and outdoor terrains that are known to be challenging for classical, model-based controllers and observe that the robot consistently learns a walking gait on all of these terrains.Finally, we evaluate our design decisions in a simulated environment.We provide videos of all real-world training and code to reproduce our results on our website: https://sites.google.com/

Topics & Concepts