Humanoid Robot RL Training

Overview

This repository shows the RL training code for the cutomized humanoid robot, featuring close-loop chain mechanism in Isaac Sim simulation.

Installation

• Install Isaac Lab by following the installation guide. We recommend using the conda installation as it simplifies calling Python scripts from the terminal.

• Using a python interpreter that has Isaac Lab installed, install the library

python -m pip install -e exts/trace_humanoid

Run the code

# Train
python scripts/rsl_rl/train.py --task Velocity-Flat-Trace_Humanoid-v0 --num_env 4096 --headless --logger tensorboard
# Play
python scripts/rsl_rl/play.py --task Velocity-Flat-Trace_Humanoid-v0 --num_env 50

Note

• Resume training from folder or checkpoint, add --resume --load_run run_folder_name --checkpoint model.pt
• Record video of a trained agent (requires installing ffmpeg), add --video --video_length 200