Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917514863181824 |
|---|---|
| author | Quartey, Benedict Castro, Sebastian Rosen, Eric Thomason, Wil Konidaris, George Tellex, Stefanie |
| author_facet | Quartey, Benedict Castro, Sebastian Rosen, Eric Thomason, Wil Konidaris, George Tellex, Stefanie |
| contents | Learning from Demonstration (LfD) enables robots to learn complex behaviors from expert examples, yet existing approaches often fail to generalize to new compositions of known skills without retraining. Modern generative policies model distributions over action trajectories alone, thus are unable to reason about the symbolic outcomes required for robust composition. We propose that skills should jointly model action trajectories and the symbolic outcomes they induce. To address this gap, we introduce Predicate Action Skills (PACTS), a class of closed-loop visuomotor policies that model skills as a joint generative process over action and predicate belief trajectories, producing coherent action-outcome rollouts within a single model. Jointly generating actions and predicates enables PACTS to learn internal representations that improve both action generation and predicate classification. Furthermore, we demonstrate zero-shot composition of learned skills via planning by leveraging online predicate predictions from PACTS as a symbolic interface for sequencing and monitoring execution. Project website: https://planpacts.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20648 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition Quartey, Benedict Castro, Sebastian Rosen, Eric Thomason, Wil Konidaris, George Tellex, Stefanie Robotics Artificial Intelligence Learning from Demonstration (LfD) enables robots to learn complex behaviors from expert examples, yet existing approaches often fail to generalize to new compositions of known skills without retraining. Modern generative policies model distributions over action trajectories alone, thus are unable to reason about the symbolic outcomes required for robust composition. We propose that skills should jointly model action trajectories and the symbolic outcomes they induce. To address this gap, we introduce Predicate Action Skills (PACTS), a class of closed-loop visuomotor policies that model skills as a joint generative process over action and predicate belief trajectories, producing coherent action-outcome rollouts within a single model. Jointly generating actions and predicates enables PACTS to learn internal representations that improve both action generation and predicate classification. Furthermore, we demonstrate zero-shot composition of learned skills via planning by leveraging online predicate predictions from PACTS as a symbolic interface for sequencing and monitoring execution. Project website: https://planpacts.github.io/ |
| title | Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2605.20648 |