Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models https://github.com/SageCao1125/Mamba-Policy Mamba Policy, a lighter yet stronger policy method based on a hybrid state space model integrated with attention mechanisms. Our extensive experiments demonstrate that Mamba Policy achieves up to a 5% improvement in success rate under a variety of manipulation datasets, while reducing the parameter count by 80%.

🔗 원본 링크

• https://github.com/SageCao1125/Mamba-Policy

미디어