X-IL: Exploring the Design Space of Imitation Learning Policies
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917928543191040 |
|---|---|
| author | Jia, Xiaogang Donat, Atalay Huang, Xi Zhao, Xuan Blessing, Denis Zhou, Hongyi Wang, Han A. Zhang, Hanyi Wang, Qian Lioutikov, Rudolf Neumann, Gerhard |
| author_facet | Jia, Xiaogang Donat, Atalay Huang, Xi Zhao, Xuan Blessing, Denis Zhou, Hongyi Wang, Han A. Zhang, Hanyi Wang, Qian Lioutikov, Rudolf Neumann, Gerhard |
| contents | Designing modern imitation learning (IL) policies requires making numerous decisions, including the selection of feature encoding, architecture, policy representation, and more. As the field rapidly advances, the range of available options continues to grow, creating a vast and largely unexplored design space for IL policies. In this work, we present X-IL, an accessible open-source framework designed to systematically explore this design space. The framework's modular design enables seamless swapping of policy components, such as backbones (e.g., Transformer, Mamba, xLSTM) and policy optimization techniques (e.g., Score-matching, Flow-matching). This flexibility facilitates comprehensive experimentation and has led to the discovery of novel policy configurations that outperform existing methods on recent robot learning benchmarks. Our experiments demonstrate not only significant performance gains but also provide valuable insights into the strengths and weaknesses of various design choices. This study serves as both a practical reference for practitioners and a foundation for guiding future research in imitation learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12330 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | X-IL: Exploring the Design Space of Imitation Learning Policies Jia, Xiaogang Donat, Atalay Huang, Xi Zhao, Xuan Blessing, Denis Zhou, Hongyi Wang, Han A. Zhang, Hanyi Wang, Qian Lioutikov, Rudolf Neumann, Gerhard Robotics Machine Learning Designing modern imitation learning (IL) policies requires making numerous decisions, including the selection of feature encoding, architecture, policy representation, and more. As the field rapidly advances, the range of available options continues to grow, creating a vast and largely unexplored design space for IL policies. In this work, we present X-IL, an accessible open-source framework designed to systematically explore this design space. The framework's modular design enables seamless swapping of policy components, such as backbones (e.g., Transformer, Mamba, xLSTM) and policy optimization techniques (e.g., Score-matching, Flow-matching). This flexibility facilitates comprehensive experimentation and has led to the discovery of novel policy configurations that outperform existing methods on recent robot learning benchmarks. Our experiments demonstrate not only significant performance gains but also provide valuable insights into the strengths and weaknesses of various design choices. This study serves as both a practical reference for practitioners and a foundation for guiding future research in imitation learning. |
| title | X-IL: Exploring the Design Space of Imitation Learning Policies |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2502.12330 |