Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2011.02671 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912091559952384 |
|---|---|
| author | Liu, Shanqi Cao, Junjie Chen, Wenzhou Wen, Licheng Liu, Yong |
| author_facet | Liu, Shanqi Cao, Junjie Chen, Wenzhou Wen, Licheng Liu, Yong |
| contents | It is challenging learning from demonstrated observation-only trajectories in a non-time-aligned environment because most imitation learning methods aim to imitate experts by following the demonstration step-by-step. However, aligned demonstrations are seldom obtainable in real-world scenarios. In this work, we propose a new imitation learning approach called Hierarchical Imitation Learning from Observation(HILONet), which adopts a hierarchical structure to choose feasible sub-goals from demonstrated observations dynamically. Our method can solve all kinds of tasks by achieving these sub-goals, whether it has a single goal position or not. We also present three different ways to increase sample efficiency in the hierarchical structure. We conduct extensive experiments using several environments. The results show the improvement in both performance and learning efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2011_02671 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | HILONet: Hierarchical Imitation Learning from Non-Aligned Observations Liu, Shanqi Cao, Junjie Chen, Wenzhou Wen, Licheng Liu, Yong Machine Learning It is challenging learning from demonstrated observation-only trajectories in a non-time-aligned environment because most imitation learning methods aim to imitate experts by following the demonstration step-by-step. However, aligned demonstrations are seldom obtainable in real-world scenarios. In this work, we propose a new imitation learning approach called Hierarchical Imitation Learning from Observation(HILONet), which adopts a hierarchical structure to choose feasible sub-goals from demonstrated observations dynamically. Our method can solve all kinds of tasks by achieving these sub-goals, whether it has a single goal position or not. We also present three different ways to increase sample efficiency in the hierarchical structure. We conduct extensive experiments using several environments. The results show the improvement in both performance and learning efficiency. |
| title | HILONet: Hierarchical Imitation Learning from Non-Aligned Observations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2011.02671 |