Efficient Learning Of Locomotion Skills Through The Discovery Of Diverse Environmental Trajectory Generator Priors

# Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors

**arXiv ID:** 2210.04819
**Authors:** Shikha Surana, Bryan Lim, Antoine Cully
**Published:** 2022-10-10T16:31:11Z
**Abstract:**
Data-driven learning based methods have recently been particularly successful at learning robust locomotion controllers for a variety of unstructured terrains. Prior work has shown that incorporating good locomotion priors in the form of trajectory generators (TGs) is effective at efficiently learning complex locomotion skills. However, defining a good, single TG as tasks/environments become increasingly more complex remains a challenging problem as it requires extensive tuning and risks reducing the effectiveness of the prior. In this paper, we present Evolved Environmental Trajectory Generators (EETG), a method that learns a diverse set of specialised locomotion priors using Quality-Diversity algorithms while maintaining a single policy within the Policies Modulating TG (PMTG) architecture. The results demonstrate that EETG enables a quadruped robot to successfully traverse a wide range of environments, such as slopes, stairs, rough terrain, and balance beams. Our experiments show that learning a diverse set of specialized TG priors is significantly (5 times) more efficient than using a single, fixed prior when dealing with a wide range of environments.

## Skill Description

This skill is generated from the arXiv paper: Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors (2210.04819).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2210.04819](http://arxiv.org/abs/2210.04819v2)