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

08/16/2022
by   Laura Smith, et al.
0

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.

READ FULL TEXT

page 1

page 6

research
07/21/2020

Deep vs. Deep Bayesian: Reinforcement Learning on a Multi-Robot Competitive Experiment

Deep Reinforcement Learning (RL) experiments are commonly performed in s...
research
09/24/2021

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

In this work, we present and study a training set-up that achieves fast ...
research
08/13/2022

Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning

Recent advances in the reinforcement learning (RL) literature have enabl...
research
09/29/2017

Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation

Enabling robots to autonomously navigate complex environments is essenti...
research
01/25/2023

DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning

Quadrupedal robots resemble the physical ability of legged animals to wa...
research
03/06/2023

Learning Humanoid Locomotion with Transformers

We present a sim-to-real learning-based approach for real-world humanoid...
research
12/13/2021

Teaching a Robot to Walk Using Reinforcement Learning

Classical control techniques such as PID and LQR have been used effectiv...

Please sign up or login with your details

Forgot password? Click here to reset