Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2412.20193 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913628785999872 |
|---|---|
| author | Fan, Jiangdong He, Hongcai Weng, Paul Xu, Hui Shao, Jie |
| author_facet | Fan, Jiangdong He, Hongcai Weng, Paul Xu, Hui Shao, Jie |
| contents | A major bottleneck in imitation learning is the requirement of a large number of expert demonstrations, which can be expensive or inaccessible. Learning from supplementary demonstrations without strict quality requirements has emerged as a powerful paradigm to address this challenge. However, previous methods often fail to fully utilize their potential by discarding non-expert data. Our key insight is that even demonstrations that fall outside the expert distribution but outperform the learned policy can enhance policy performance. To utilize this potential, we propose a novel approach named imitation learning via meta-learning an action ranker (ILMAR). ILMAR implements weighted behavior cloning (weighted BC) on a limited set of expert demonstrations along with supplementary demonstrations. It utilizes the functional of the advantage function to selectively integrate knowledge from the supplementary demonstrations. To make more effective use of supplementary demonstrations, we introduce meta-goal in ILMAR to optimize the functional of the advantage function by explicitly minimizing the distance between the current policy and the expert policy. Comprehensive experiments using extensive tasks demonstrate that ILMAR significantly outperforms previous methods in handling suboptimal demonstrations. Code is available at https://github.com/F-GOD6/ILMAR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20193 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker Fan, Jiangdong He, Hongcai Weng, Paul Xu, Hui Shao, Jie Machine Learning Artificial Intelligence A major bottleneck in imitation learning is the requirement of a large number of expert demonstrations, which can be expensive or inaccessible. Learning from supplementary demonstrations without strict quality requirements has emerged as a powerful paradigm to address this challenge. However, previous methods often fail to fully utilize their potential by discarding non-expert data. Our key insight is that even demonstrations that fall outside the expert distribution but outperform the learned policy can enhance policy performance. To utilize this potential, we propose a novel approach named imitation learning via meta-learning an action ranker (ILMAR). ILMAR implements weighted behavior cloning (weighted BC) on a limited set of expert demonstrations along with supplementary demonstrations. It utilizes the functional of the advantage function to selectively integrate knowledge from the supplementary demonstrations. To make more effective use of supplementary demonstrations, we introduce meta-goal in ILMAR to optimize the functional of the advantage function by explicitly minimizing the distance between the current policy and the expert policy. Comprehensive experiments using extensive tasks demonstrate that ILMAR significantly outperforms previous methods in handling suboptimal demonstrations. Code is available at https://github.com/F-GOD6/ILMAR. |
| title | Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.20193 |