PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908868745887744 |
|---|---|
| author | Boix-Granell, Arnau San-Miguel-Tello, Alberto Dalmau-Moreno, Magí García, Néstor |
| author_facet | Boix-Granell, Arnau San-Miguel-Tello, Alberto Dalmau-Moreno, Magí García, Néstor |
| contents | This paper presents PRISM: an instruction-conditioned refinement method for imitation policies in robotic manipulation. This approach bridges Imitation Learning (IL) and Reinforcement Learning (RL) frameworks into a seamless pipeline, such that an imitation policy on a broad generic task, generated from a set of user-guided demonstrations, can be refined through reinforcement to generate new unseen fine-grain behaviours. The refinement process follows the Eureka paradigm, where reward functions for RL are iteratively generated from an initial natural-language task description. Presented approach, builds on top of this mechanism to adapt a refined IL policy of a generic task to new goal configurations and the introduction of constraints by adding also human feedback correction on intermediate rollouts, enabling policy reusability and therefore data efficiency. Results for a pick-and-place task in a simulated scenario show that proposed method outperforms policies without human feedback, improving robustness on deployment and reducing computational burden. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05574 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions Boix-Granell, Arnau San-Miguel-Tello, Alberto Dalmau-Moreno, Magí García, Néstor Robotics Artificial Intelligence This paper presents PRISM: an instruction-conditioned refinement method for imitation policies in robotic manipulation. This approach bridges Imitation Learning (IL) and Reinforcement Learning (RL) frameworks into a seamless pipeline, such that an imitation policy on a broad generic task, generated from a set of user-guided demonstrations, can be refined through reinforcement to generate new unseen fine-grain behaviours. The refinement process follows the Eureka paradigm, where reward functions for RL are iteratively generated from an initial natural-language task description. Presented approach, builds on top of this mechanism to adapt a refined IL policy of a generic task to new goal configurations and the introduction of constraints by adding also human feedback correction on intermediate rollouts, enabling policy reusability and therefore data efficiency. Results for a pick-and-place task in a simulated scenario show that proposed method outperforms policies without human feedback, improving robustness on deployment and reducing computational burden. |
| title | PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2603.05574 |