collaborators

6 papers

cs.LG2026

Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning

Yannik Schnitzer, Mathias Jackermeier, Alessandro Abate +1

Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide…

cs.LG2026

PlatoLTL: Learning to Generalize Across Symbols in LTL Instructions for Multi-Task RL

Jacques Cloete, Mathias Jackermeier, Ioannis Havoutis +1

A central challenge in multi-task reinforcement learning (RL) is to train generalist policies capable of performing tasks not seen during training. To facilitate such generalizatio…

cs.LG2026

Zero-Shot Instruction Following in RL via Structured LTL Representations

Mathias Jackermeier, Mattia Giuri, Jacques Cloete +1

We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training. In this setting, linear temporal lo…

cs.AI2026

Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions

Alessandro Abate, Giuseppe De Giacomo, Mathias Jackermeier +4

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 consi…

cs.AI2025

Zero-Shot Instruction Following in RL via Structured LTL Representations

Mattia Giuri, Mathias Jackermeier, Alessandro Abate

Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents. Recent work has shown that interpreting LTL i…

cs.AI2025

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL

Mathias Jackermeier, Alessandro Abate

Linear temporal logic (LTL) has recently been adopted as a powerful formalism for specifying complex, temporally extended tasks in multi-task reinforcement learning (RL). However,…