Visual Hindsight Self-Imitation Learning for Interactive Navigation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929391561342976 |
|---|---|
| author | Kim, Kibeom Shin, Kisung Lee, Min Whoo Lee, Moonhoen Lee, Minsu Zhang, Byoung-Tak |
| author_facet | Kim, Kibeom Shin, Kisung Lee, Min Whoo Lee, Moonhoen Lee, Minsu Zhang, Byoung-Tak |
| contents | Interactive visual navigation tasks, which involve following instructions to reach and interact with specific targets, are challenging not only because successful experiences are very rare but also because the complex visual inputs require a substantial number of samples. Previous methods for these tasks often rely on intricately designed dense rewards or the use of expensive expert data for imitation learning. To tackle these challenges, we propose a novel approach, Visual Hindsight Self-Imitation Learning (VHS) for enhancing sample efficiency through hindsight goal re-labeling and self-imitation. We also introduce a prototypical goal embedding method derived from experienced goal observations, that is particularly effective in vision-based and partially observable environments. This embedding technique allows the agent to visually reinterpret its unsuccessful attempts, enabling vision-based goal re-labeling and self-imitation from enhanced successful experiences. Experimental results show that VHS outperforms existing techniques in interactive visual navigation tasks, confirming its superior performance and sample efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_03446 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Visual Hindsight Self-Imitation Learning for Interactive Navigation Kim, Kibeom Shin, Kisung Lee, Min Whoo Lee, Moonhoen Lee, Minsu Zhang, Byoung-Tak Artificial Intelligence Interactive visual navigation tasks, which involve following instructions to reach and interact with specific targets, are challenging not only because successful experiences are very rare but also because the complex visual inputs require a substantial number of samples. Previous methods for these tasks often rely on intricately designed dense rewards or the use of expensive expert data for imitation learning. To tackle these challenges, we propose a novel approach, Visual Hindsight Self-Imitation Learning (VHS) for enhancing sample efficiency through hindsight goal re-labeling and self-imitation. We also introduce a prototypical goal embedding method derived from experienced goal observations, that is particularly effective in vision-based and partially observable environments. This embedding technique allows the agent to visually reinterpret its unsuccessful attempts, enabling vision-based goal re-labeling and self-imitation from enhanced successful experiences. Experimental results show that VHS outperforms existing techniques in interactive visual navigation tasks, confirming its superior performance and sample efficiency. |
| title | Visual Hindsight Self-Imitation Learning for Interactive Navigation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2312.03446 |