Reinforcement Learning methods with advanced optimization techniques

RLopt combines state-of-the-art reinforcement learning algorithms with advanced optimization techniques. This library provides efficient implementations for training RL agents with optimized performance.

• Integration with popular RL frameworks (Stable-Baselines3, TorchRL)
• Advanced optimization algorithms
• Configurable training pipelines using Hydra
• Experiment tracking with WandB

For training RL agents in IsaacLab, please refer to the IsaacLab documentation and our forked version.

• Python 3.10 or higher
• PyTorch
• CUDA-compatible GPU (recommended for faster training)

pip install .

Stay tuned for the official documentation.

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see the LICENSE file for details.