Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913723321417728 |
|---|---|
| author | Lorang, Pierrick Lu, Hong Scheutz, Matthias |
| author_facet | Lorang, Pierrick Lu, Hong Scheutz, Matthias |
| contents | Adapting quickly to dynamic, uncertain environments-often called "open worlds"-remains a major challenge in robotics. Traditional Task and Motion Planning (TAMP) approaches struggle to cope with unforeseen changes, are data-inefficient when adapting, and do not leverage world models during learning. We address this issue with a hybrid planning and learning system that integrates two models: a low level neural network based model that learns stochastic transitions and drives exploration via an Intrinsic Curiosity Module (ICM), and a high level symbolic planning model that captures abstract transitions using operators, enabling the agent to plan in an "imaginary" space and generate reward machines. Our evaluation in a robotic manipulation domain with sequential novelty injections demonstrates that our approach converges faster and outperforms state-of-the-art hybrid methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04931 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation Lorang, Pierrick Lu, Hong Scheutz, Matthias Robotics Artificial Intelligence Adapting quickly to dynamic, uncertain environments-often called "open worlds"-remains a major challenge in robotics. Traditional Task and Motion Planning (TAMP) approaches struggle to cope with unforeseen changes, are data-inefficient when adapting, and do not leverage world models during learning. We address this issue with a hybrid planning and learning system that integrates two models: a low level neural network based model that learns stochastic transitions and drives exploration via an Intrinsic Curiosity Module (ICM), and a high level symbolic planning model that captures abstract transitions using operators, enabling the agent to plan in an "imaginary" space and generate reward machines. Our evaluation in a robotic manipulation domain with sequential novelty injections demonstrates that our approach converges faster and outperforms state-of-the-art hybrid methods. |
| title | Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2503.04931 |