CusLab: Direct IsaacLab Workflow using CusRL

A robotics simulation framework for legged robots built on Isaac Lab & Cusrl, focusing on legged robot control using Deep Reinforcement Learning.

📋 Requirements

• Python 3.11
• Isaac Lab (see installation guide)
• CUDA-capable GPU (recommended)

🛠️ Installation

1. Clone the repository

git clone https://github.com/legnAray/CusLab.git
cd CusLab

2. Install Isaac Lab

Follow the official Isaac Lab installation guide.

3. Install CusLab

pip install -e .

# For development (optional)
pip install -e ".[dev]"

4. Setup pre-commit hooks (for development)

pre-commit install

🏃 Quick Start

List Available Environments

python scripts/list_envs.py

Training with CusRL

# Train a policy
python scripts/cusrl/train.py --task g1_base --run_name your_experiment --headless

# Play with trained model
python scripts/cusrl/play.py --task g1_base --run_name your_experiment

# Export trained model
python scripts/cusrl/export.py --task g1_base --run_name your_experiment

References and Thanks

• IsaacLab
• LeggedLab
• CusRL