# Bioinspired morphology and task curricula for learning locomotion in bipedal muscle-actuated systems

## TL;DR

This paper introduces a learning approach for bipedal robots inspired by human development, enabling them to learn walking and running skills more effectively.

## Contribution

The novel double curriculum approach combines task and morphology learning to improve locomotion in musculoskeletal systems.

## Key findings

- The method outperforms state-of-the-art exploration techniques in musculoskeletal systems.
- Robust gaits are learned that adapt to varying velocities and perturbations.
- The approach is agnostic to the RL algorithm and does not require reward tuning or demonstrations.

## Abstract

Humans master complex motor skills such as walking and running through a sophisticated blend of learning and adaptation. Replicating this level of skill acquisition with traditional Reinforcement Learning (RL) methods in musculoskeletal humanoid systems is challenging due to intricate control dynamics and over-actuation. Inspired by human developmental learning, here we address these challenges, with a double curriculum approach: a three-stage task curriculum (balance, walk, run) and an up to three-stage morphology curriculum (4 year-old, 12 year-old, adult), mimicking physical growth. This combined approach enables the agent to efficiently learn robust gaits that are adaptable to varying velocities and perturbations. Extensive analysis and ablation studies demonstrate that our method outperforms state-of-the-art exploration techniques for musculoskeletal systems. Our approach is agnostic to the underlying RL algorithm and does not require reward tuning, demonstrations, or specific muscular architecture information, marking a notable advancement in the field.

Achieving locomotion in musculoskeletal humanoid systems is a challenge for reinforcement learning. Badie and colleagues propose a curriculum combining physical growth and skill progression to develop gaits adaptable to varying speeds and terrains.