Showing 2026Show all
2 papers · 1 filter
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.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…