Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909364118355968 |
|---|---|
| author | Wang, Yixiao Zhang, Yifei Huo, Mingxiao Tian, Ran Zhang, Xiang Xie, Yichen Xu, Chenfeng Ji, Pengliang Zhan, Wei Ding, Mingyu Tomizuka, Masayoshi |
| author_facet | Wang, Yixiao Zhang, Yifei Huo, Mingxiao Tian, Ran Zhang, Xiang Xie, Yichen Xu, Chenfeng Ji, Pengliang Zhan, Wei Ding, Mingyu Tomizuka, Masayoshi |
| contents | The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the entire model. SDP not only reduces the burden of active parameters but also facilitates the seamless integration and reuse of experts across various tasks. Extensive experiments on diverse tasks in both simulations and real world show that SDP 1) excels in multitask scenarios with negligible increases in active parameters, 2) prevents forgetting in continual learning of new tasks, and 3) enables efficient task transfer, offering a promising solution for advanced robotic applications. Demos and codes can be found in https://forrest-110.github.io/sparse_diffusion_policy/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01531 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning Wang, Yixiao Zhang, Yifei Huo, Mingxiao Tian, Ran Zhang, Xiang Xie, Yichen Xu, Chenfeng Ji, Pengliang Zhan, Wei Ding, Mingyu Tomizuka, Masayoshi Robotics Machine Learning The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the entire model. SDP not only reduces the burden of active parameters but also facilitates the seamless integration and reuse of experts across various tasks. Extensive experiments on diverse tasks in both simulations and real world show that SDP 1) excels in multitask scenarios with negligible increases in active parameters, 2) prevents forgetting in continual learning of new tasks, and 3) enables efficient task transfer, offering a promising solution for advanced robotic applications. Demos and codes can be found in https://forrest-110.github.io/sparse_diffusion_policy/. |
| title | Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2407.01531 |