# Robust Satisfaction of Temporal Logic Specifications via Reinforcement Learning

arXiv: https://arxiv.org/abs/1510.06460 · HTML: https://mlsanity.com/paper/1510.06460/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2015.

## Built on by (most cited first, 2 of 2)

- [Hierarchical Potential-based Reward Shaping from Task Specifications](https://mlsanity.com/paper/2110.02792/) (2021)
- [Safe Policy Improvement in Constrained Markov Decision Processes](https://mlsanity.com/paper/2210.11259/) (2022)

## Abstract (arXiv)

We consider the problem of steering a system with unknown, stochastic dynamics to satisfy a rich, temporally layered task given as a signal temporal logic formula. We represent the system as a Markov decision process in which the states are built from a partition of the state space and the transition probabilities are unknown. We present provably convergent reinforcement learning algorithms to maximize the probability of satisfying a given formula and to maximize the average expected robustness, i.e., a measure of how strongly the formula is satisfied. We demonstrate via a pair of robot navigation simulation case studies that reinforcement learning with robustness maximization performs better than probability maximization in terms of both probability of satisfaction and expected robustness.