WayEx: Waypoint Exploration using a Single Demonstration

TL;DR

WayEx is a novel method enabling robots to learn complex tasks from a single demonstration by using a new reward function and knowledge expansion, significantly reducing training time and outperforming existing imitation methods.

Contribution

WayEx introduces a waypoint exploration strategy that learns from a single demonstration without action information, advancing imitation learning efficiency and effectiveness.

Findings

Reduces training time by 50% compared to traditional methods.

Achieves higher rewards than existing imitation learning with one demonstration.

Successfully handles complex environments where standard approaches fail.

Abstract

We propose WayEx, a new method for learning complex goal-conditioned robotics tasks from a single demonstration. Our approach distinguishes itself from existing imitation learning methods by demanding fewer expert examples and eliminating the need for information about the actions taken during the demonstration. This is accomplished by introducing a new reward function and employing a knowledge expansion technique. We demonstrate the effectiveness of WayEx, our waypoint exploration strategy, across six diverse tasks, showcasing its applicability in various environments. Notably, our method significantly reduces training time by 50% as compared to traditional reinforcement learning methods. WayEx obtains a higher reward than existing imitation learning methods given only a single demonstration. Furthermore, we demonstrate its success in tackling complex environments where standard approaches fall short. More information is available at: https://waypoint-ex.github.io.