This is the pre-proceedings for the RLC 2026. You may expect minor changes.
Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
Will be presented at the Reinforcement Learning Conference (RLC), Montréal, Quebec, Canada, August 15–17, 2026.
Keywords: Neurosymbolic Reinforcement Learning, Temporal Specifications, Multi-Task
In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied on knowledge of the mapping between raw observations and symbols appearing in the formulae. We drop this unrealistic assumption by jointly training a multi-task policy and a symbol grounder with the same experience. The symbol grounder is trained only from raw observations and sparse rewards via Neural Reward Machines in a semi-supervised fashion. Experiments on vision-based environments show that our method achieves performance comparable to using the true symbol grounding and significantly outperforms state-of-the-art methods for sub-symbolic environments.
Matteo Pannacci, Andrea Fanti, Elena Umili, and Roberto Capobianco. "Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization." Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
BibTeX:@article{pannacci2026grounding,
title={Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization},
author={Matteo Pannacci and Andrea Fanti and Elena Umili and Roberto Capobianco},
journal={Reinforcement Learning Journal},
volume={7},
pages={},
year={2026}
}