The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917079314071552 |
|---|---|
| author | Tsagkas, Nikolaos Sochopoulos, Andreas Danier, Duolikun Lu, Chris Xiaoxuan Mac Aodha, Oisin |
| author_facet | Tsagkas, Nikolaos Sochopoulos, Andreas Danier, Duolikun Lu, Chris Xiaoxuan Mac Aodha, Oisin |
| contents | The integration of pre-trained visual representations (PVRs) has significantly advanced visuomotor policy learning. However, effectively leveraging these models remains a challenge. We identify temporal entanglement as a critical, inherent issue when using these time-invariant models in sequential decision-making tasks. This entanglement arises because PVRs, optimised for static image understanding, struggle to represent the temporal dependencies crucial for visuomotor control. In this work, we quantify the impact of temporal entanglement, demonstrating a strong correlation between a policy's success rate and the ability of its latent space to capture task-progression cues. Based on these insights, we propose a simple, yet effective disentanglement baseline designed to mitigate temporal entanglement. Our empirical results show that traditional methods aimed at enriching features with temporal components are insufficient on their own, highlighting the necessity of explicitly addressing temporal disentanglement for robust visuomotor policy learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03270 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning Tsagkas, Nikolaos Sochopoulos, Andreas Danier, Duolikun Lu, Chris Xiaoxuan Mac Aodha, Oisin Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning The integration of pre-trained visual representations (PVRs) has significantly advanced visuomotor policy learning. However, effectively leveraging these models remains a challenge. We identify temporal entanglement as a critical, inherent issue when using these time-invariant models in sequential decision-making tasks. This entanglement arises because PVRs, optimised for static image understanding, struggle to represent the temporal dependencies crucial for visuomotor control. In this work, we quantify the impact of temporal entanglement, demonstrating a strong correlation between a policy's success rate and the ability of its latent space to capture task-progression cues. Based on these insights, we propose a simple, yet effective disentanglement baseline designed to mitigate temporal entanglement. Our empirical results show that traditional methods aimed at enriching features with temporal components are insufficient on their own, highlighting the necessity of explicitly addressing temporal disentanglement for robust visuomotor policy learning. |
| title | The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2502.03270 |