Visual Imitation Learning with Calibrated Contrastive Representation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913202730696704 |
|---|---|
| author | Wang, Yunke Tao, Linwei Du, Bo Lin, Yutian Xu, Chang |
| author_facet | Wang, Yunke Tao, Linwei Du, Bo Lin, Yutian Xu, Chang |
| contents | Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. However, challenges arise in handling visual states due to their less distinguishable representation compared to low-dimensional proprioceptive features. While existing methods resort to adopt complex network architectures or separate the process of learning representation and decision-making, they overlook valuable intra-agent information within demonstrations. To address this problem, this paper proposes a simple and effective solution by incorporating calibrated contrastive representative learning into visual AIL framework. Specifically, we present an image encoder in visual AIL, utilizing a combination of unsupervised and supervised contrastive learning to extract valuable features from visual states. Based on the fact that the improved agent often produces demonstrations of varying quality, we propose to calibrate the contrastive loss by treating each agent demonstrations as a mixed sample. The incorporation of contrastive learning can be jointly optimized with the AIL framework, without modifying the architecture or incurring significant computational costs. Experimental results on DMControl Suite demonstrate our proposed method is sample efficient and can outperform other compared methods from different aspects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11396 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visual Imitation Learning with Calibrated Contrastive Representation Wang, Yunke Tao, Linwei Du, Bo Lin, Yutian Xu, Chang Machine Learning Computer Vision and Pattern Recognition Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions. However, challenges arise in handling visual states due to their less distinguishable representation compared to low-dimensional proprioceptive features. While existing methods resort to adopt complex network architectures or separate the process of learning representation and decision-making, they overlook valuable intra-agent information within demonstrations. To address this problem, this paper proposes a simple and effective solution by incorporating calibrated contrastive representative learning into visual AIL framework. Specifically, we present an image encoder in visual AIL, utilizing a combination of unsupervised and supervised contrastive learning to extract valuable features from visual states. Based on the fact that the improved agent often produces demonstrations of varying quality, we propose to calibrate the contrastive loss by treating each agent demonstrations as a mixed sample. The incorporation of contrastive learning can be jointly optimized with the AIL framework, without modifying the architecture or incurring significant computational costs. Experimental results on DMControl Suite demonstrate our proposed method is sample efficient and can outperform other compared methods from different aspects. |
| title | Visual Imitation Learning with Calibrated Contrastive Representation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.11396 |