Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912884669284352 |
|---|---|
| author | Abate, Alessandro De Giacomo, Giuseppe Jackermeier, Mathias Kretínský, Jan Prokop, Maximilian Weinhuber, Christoph |
| author_facet | Abate, Alessandro De Giacomo, Giuseppe Jackermeier, Mathias Kretínský, Jan Prokop, Maximilian Weinhuber, Christoph |
| contents | We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks. We consider tasks specified as linear temporal logic (LTL) formulae, which are commonly used in formal methods to specify properties of systems, and have recently been successfully adopted in RL. In this setting, we present a novel task embedding technique leveraging a new generation of semantic LTL-to-automata translations, originally developed for temporal synthesis. The resulting semantically labelled automata contain rich, structured information in each state that allow us to (i) compute the automaton efficiently on-the-fly, (ii) extract expressive task embeddings used to condition the policy, and (iii) naturally support full LTL. Experimental results in a variety of domains demonstrate that our approach achieves state-of-the-art performance and is able to scale to complex specifications where existing methods fail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06746 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions Abate, Alessandro De Giacomo, Giuseppe Jackermeier, Mathias Kretínský, Jan Prokop, Maximilian Weinhuber, Christoph Artificial Intelligence Machine Learning We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy capable of generalising to arbitrary, possibly unseen tasks. We consider tasks specified as linear temporal logic (LTL) formulae, which are commonly used in formal methods to specify properties of systems, and have recently been successfully adopted in RL. In this setting, we present a novel task embedding technique leveraging a new generation of semantic LTL-to-automata translations, originally developed for temporal synthesis. The resulting semantically labelled automata contain rich, structured information in each state that allow us to (i) compute the automaton efficiently on-the-fly, (ii) extract expressive task embeddings used to condition the policy, and (iii) naturally support full LTL. Experimental results in a variety of domains demonstrate that our approach achieves state-of-the-art performance and is able to scale to complex specifications where existing methods fail. |
| title | Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.06746 |