A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914072429068288 |
|---|---|
| author | Wang, Yilin Li, Shangzhe Niu, Haoyi Huang, Zhiao Zhang, Weitong Su, Hao |
| author_facet | Wang, Yilin Li, Shangzhe Niu, Haoyi Huang, Zhiao Zhang, Weitong Su, Hao |
| contents | We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a solution that leverages robot simulators to achieve online imitation learning. Our sim-to-real framework is based on world models and combines online imitation pretraining with offline finetuning. By leveraging online interactions, our approach alleviates the data coverage limitations of offline methods, leading to improved robustness and reduced performance degradation during finetuning. It also enhances generalization during domain transfer. Our empirical results demonstrate its effectiveness, improving success rates by at least 31.7% in sim-to-sim transfer and 23.3% in sim-to-real transfer over existing offline imitation learning baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models Wang, Yilin Li, Shangzhe Niu, Haoyi Huang, Zhiao Zhang, Weitong Su, Hao Robotics We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a solution that leverages robot simulators to achieve online imitation learning. Our sim-to-real framework is based on world models and combines online imitation pretraining with offline finetuning. By leveraging online interactions, our approach alleviates the data coverage limitations of offline methods, leading to improved robustness and reduced performance degradation during finetuning. It also enhances generalization during domain transfer. Our empirical results demonstrate its effectiveness, improving success rates by at least 31.7% in sim-to-sim transfer and 23.3% in sim-to-real transfer over existing offline imitation learning baselines. |
| title | A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2510.02538 |