Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915151782871040 |
|---|---|
| author | Kim, Minung Lee, Kawon Kim, Jungmo Choi, Sungho Han, Seungyul |
| author_facet | Kim, Minung Lee, Kawon Kim, Jungmo Choi, Sungho Han, Seungyul |
| contents | Imitation learning (IL) enables agents to mimic expert behavior without reward signals but faces challenges in cross-domain scenarios with high-dimensional, noisy, and incomplete visual observations. To address this, we propose Domain-Invariant Per-Frame Feature Extraction for Imitation Learning (DIFF-IL), a novel IL method that extracts domain-invariant features from individual frames and adapts them into sequences to isolate and replicate expert behaviors. We also introduce a frame-wise time labeling technique to segment expert behaviors by timesteps and assign rewards aligned with temporal contexts, enhancing task performance. Experiments across diverse visual environments demonstrate the effectiveness of DIFF-IL in addressing complex visual tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02867 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations Kim, Minung Lee, Kawon Kim, Jungmo Choi, Sungho Han, Seungyul Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Imitation learning (IL) enables agents to mimic expert behavior without reward signals but faces challenges in cross-domain scenarios with high-dimensional, noisy, and incomplete visual observations. To address this, we propose Domain-Invariant Per-Frame Feature Extraction for Imitation Learning (DIFF-IL), a novel IL method that extracts domain-invariant features from individual frames and adapts them into sequences to isolate and replicate expert behaviors. We also introduce a frame-wise time labeling technique to segment expert behaviors by timesteps and assign rewards aligned with temporal contexts, enhancing task performance. Experiments across diverse visual environments demonstrate the effectiveness of DIFF-IL in addressing complex visual tasks. |
| title | Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.02867 |