KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910653735763968 |
|---|---|
| author | Lu, Jingxian Xia, Wenke Wang, Dong Wang, Zhigang Zhao, Bin Hu, Di Li, Xuelong |
| author_facet | Lu, Jingxian Xia, Wenke Wang, Dong Wang, Zhigang Zhao, Bin Hu, Di Li, Xuelong |
| contents | Online Imitation Learning struggles with the gap between extensive online exploration space and limited expert trajectories, hindering efficient exploration due to inaccurate reward estimation. Inspired by the findings from cognitive neuroscience, we hypothesize that an agent could estimate precise task-aware reward for efficient online exploration, through decomposing the target task into the objectives of "what to do" and the mechanisms of "how to do". In this work, we introduce the hybrid Key-state guided Online Imitation (KOI) learning method, which leverages the integration of semantic and motion key states as guidance for reward estimation. Initially, we utilize visual-language models to extract semantic key states from expert trajectory, indicating the objectives of "what to do". Within the intervals between semantic key states, optical flow is employed to capture motion key states to understand the mechanisms of "how to do". By integrating a thorough grasp of hybrid key states, we refine the trajectory-matching reward computation, accelerating online imitation learning with task-aware exploration. We evaluate not only the success rate of the tasks in the Meta-World and LIBERO environments, but also the trend of variance during online imitation learning, proving that our method is more sample efficient. We also conduct real-world robotic manipulation experiments to validate the efficacy of our method, demonstrating the practical applicability of our KOI method. Videos and code are available at https://gewu-lab.github.io/Keystate_Online_Imitation/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02912 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance Lu, Jingxian Xia, Wenke Wang, Dong Wang, Zhigang Zhao, Bin Hu, Di Li, Xuelong Robotics Artificial Intelligence Online Imitation Learning struggles with the gap between extensive online exploration space and limited expert trajectories, hindering efficient exploration due to inaccurate reward estimation. Inspired by the findings from cognitive neuroscience, we hypothesize that an agent could estimate precise task-aware reward for efficient online exploration, through decomposing the target task into the objectives of "what to do" and the mechanisms of "how to do". In this work, we introduce the hybrid Key-state guided Online Imitation (KOI) learning method, which leverages the integration of semantic and motion key states as guidance for reward estimation. Initially, we utilize visual-language models to extract semantic key states from expert trajectory, indicating the objectives of "what to do". Within the intervals between semantic key states, optical flow is employed to capture motion key states to understand the mechanisms of "how to do". By integrating a thorough grasp of hybrid key states, we refine the trajectory-matching reward computation, accelerating online imitation learning with task-aware exploration. We evaluate not only the success rate of the tasks in the Meta-World and LIBERO environments, but also the trend of variance during online imitation learning, proving that our method is more sample efficient. We also conduct real-world robotic manipulation experiments to validate the efficacy of our method, demonstrating the practical applicability of our KOI method. Videos and code are available at https://gewu-lab.github.io/Keystate_Online_Imitation/. |
| title | KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2408.02912 |