This repo contains implementation of the paper Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning
This repo requires the following packages:
- Isaac Gym
- Legged Gym
- RSL-RL
To install Isaac Gym, go to the link and follow the instructions on the page.
-
clone this repo
cd rsl_rl-1.0.2
pip install -e .
cd .. cd legged_gym
pip install -e .
cd ..To train your robot run
python3 legged_gym/scripts/train.py --task=[robot name] To evaluate the trained policy run
python3 legged_gym/scripts/play.py --task=[robot name]Go1:
Requires python 3.8 and numpy version<=1.24.
