From Knowing to Doing: Learning Diverse Motor Skills through Instruction Learning

TL;DR

This paper introduces instruction learning, a novel approach for robot motor skill acquisition that combines feedforward instructions with reinforcement learning, resulting in faster, more flexible, and efficient learning compared to imitation learning.

Contribution

The paper proposes instruction learning, a new method that directly uses instructions as feedforward actions, removing the need for mimic rewards and improving learning efficiency and flexibility.

Findings

Instruction learning speeds up training significantly.

It guarantees learning of desired motions.

Effective in sim-to-real transfer and online learning.

Abstract

Recent years have witnessed many successful trials in the robot learning field. For contact-rich robotic tasks, it is challenging to learn coordinated motor skills by reinforcement learning. Imitation learning solves this problem by using a mimic reward to encourage the robot to track a given reference trajectory. However, imitation learning is not so efficient and may constrain the learned motion. In this paper, we propose instruction learning, which is inspired by the human learning process and is highly efficient, flexible, and versatile for robot motion learning. Instead of using a reference signal in the reward, instruction learning applies a reference signal directly as a feedforward action, and it is combined with a feedback action learned by reinforcement learning to control the robot. Besides, we propose the action bounding technique and remove the mimic reward, which is shown to be crucial for efficient and flexible learning. We compare the performance of instruction learning with imitation learning, indicating that instruction learning can greatly speed up the training process and guarantee learning the desired motion correctly. The effectiveness of instruction learning is validated through a bunch of motion learning examples for a biped robot and a quadruped robot, where skills can be learned typically within several million steps. Besides, we also conduct sim-to-real transfer and online learning experiments on a real quadruped robot. Instruction learning has shown great merits and potential, making it a promising alternative for imitation learning.