World Models as Reference Trajectories for Rapid Motor Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916749594591232 |
|---|---|
| author | Brito, Carlos Stein McNamee, Daniel |
| author_facet | Brito, Carlos Stein McNamee, Daniel |
| contents | Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a dual control framework that uses world model predictions as implicit reference trajectories for rapid adaptation. Our method separates the control problem into long-term reward maximization through reinforcement learning and robust motor execution through rapid latent control. This dual architecture achieves significantly faster adaptation with low online computational cost compared to model-based RL baselines, while maintaining near-optimal performance. The approach combines the benefits of flexible policy learning through reinforcement learning with rapid error correction capabilities, providing a principled approach to maintaining performance in high-dimensional continuous control tasks under varying dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15589 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | World Models as Reference Trajectories for Rapid Motor Adaptation Brito, Carlos Stein McNamee, Daniel Machine Learning Artificial Intelligence Robotics Systems and Control Deploying learned control policies in real-world environments poses a fundamental challenge. When system dynamics change unexpectedly, performance degrades until models are retrained on new data. We introduce Reflexive World Models (RWM), a dual control framework that uses world model predictions as implicit reference trajectories for rapid adaptation. Our method separates the control problem into long-term reward maximization through reinforcement learning and robust motor execution through rapid latent control. This dual architecture achieves significantly faster adaptation with low online computational cost compared to model-based RL baselines, while maintaining near-optimal performance. The approach combines the benefits of flexible policy learning through reinforcement learning with rapid error correction capabilities, providing a principled approach to maintaining performance in high-dimensional continuous control tasks under varying dynamics. |
| title | World Models as Reference Trajectories for Rapid Motor Adaptation |
| topic | Machine Learning Artificial Intelligence Robotics Systems and Control |
| url | https://arxiv.org/abs/2505.15589 |