# Learning-Based Synthesis of Safety Controllers

arXiv: https://arxiv.org/abs/1901.06801 · HTML: https://mlsanity.com/paper/1901.06801/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2019.

## Built on by (most cited first, 3 of 3)

- [dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts](https://mlsanity.com/paper/2101.07202/) (2021)
- [Explaining Control Policies through Predicate Decision Diagrams](https://mlsanity.com/paper/2503.06420/) (2025)
- [Explainable Representation of Finite-Memory Policies for POMDPs using Decision Trees](https://mlsanity.com/paper/2411.13365/) (2024)

## Abstract (arXiv)

We propose a machine learning framework to synthesize reactive controllers for systems whose interactions with their adversarial environment are modeled by infinite-duration, two-player games over (potentially) infinite graphs. Our framework targets safety games with infinitely many vertices, but it is also applicable to safety games over finite graphs whose size is too prohibitive for conventional synthesis techniques. The learning takes place in a feedback loop between a teacher component, which can reason symbolically about the safety game, and a learning algorithm, which successively learns an overapproximation of the winning region from various kinds of examples provided by the teacher. We develop a novel decision tree learning algorithm for this setting and show that our algorithm is guaranteed to converge to a reactive safety controller if a suitable overapproximation of the winning region can be expressed as a decision tree. Finally, we empirically compare the performance of a prototype implementation to existing approaches, which are based on constraint solving and automata learning, respectively.