English

Certified Reinforcement Learning with Logic Guidance

Machine Learning 2023-06-07 v4 Machine Learning

Abstract

Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs). The given LTL property is translated into a Limit-Deterministic Generalised Buchi Automaton (LDGBA), which is then used to shape a synchronous reward function on-the-fly. Under certain assumptions, the algorithm is guaranteed to synthesise a control policy whose traces satisfy the LTL specification with maximal probability.

Keywords

Cite

@article{arxiv.1902.00778,
  title  = {Certified Reinforcement Learning with Logic Guidance},
  author = {Hosein Hasanbeig and Daniel Kroening and Alessandro Abate},
  journal= {arXiv preprint arXiv:1902.00778},
  year   = {2023}
}
R2 v1 2026-06-23T07:30:27.287Z