{"type":"ScholarlyArticle","title":"Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions","authors":[{"name":"Alessandro Abate","slug":"alessandro-abate","given":"Alessandro","family":"Abate","affiliation":""},{"name":"Giuseppe De Giacomo","slug":"giuseppe-de-giacomo","given":"Giuseppe","family":"De Giacomo","affiliation":""},{"name":"Mathias Jackermeier","slug":"mathias-jackermeier","given":"Mathias","family":"Jackermeier","affiliation":""},{"name":"Jan Křetínský","slug":"jan-kretinsky","given":"Jan","family":"Křetínský","affiliation":""},{"name":"Maximilian Prokop","slug":"maximilian-prokop","given":"Maximilian","family":"Prokop","affiliation":""},{"name":"Christoph Weinhuber","slug":"christoph-weinhuber","given":"Christoph","family":"Weinhuber","affiliation":""}],"abstract":"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.","doi":"10.24963/ijcai.2026/1","url":"https://ijcai.org/proceedings/2026/1","pdf":"https://ijcai.org/proceedings/2026/0001.pdf","markdown":"https://ijcai.org/proceedings/2026/1.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/1","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":1,"pages":{"first":3,"last":11},"keywords":["Knowledge Representation and Reasoning: Reasoning about actions","Knowledge Representation and Reasoning: Learning and reasoning","Machine Learning: Multi-task and transfer learning","Agent-based and Multi-agent Systems: Formal verification, validation and synthesis","Machine Learning: Reinforcement learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}