# STL2vec: Signal Temporal Logic Embeddings for Control Synthesis With Recurrent Neural Networks

arXiv: https://arxiv.org/abs/2109.04636 · HTML: https://mlsanity.com/paper/2109.04636/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2021.

## Built on by (most cited first, 7 of 7)

- [Signal Temporal Logic Neural Predictive Control](https://mlsanity.com/paper/2309.05131/) (2023)
- [Follow The Rules: Online Signal Temporal Logic Tree Search for Guided Imitation Learning in Stochastic Domains](https://mlsanity.com/paper/2209.13737/) (2022)
- [stl2vec: Semantic and Interpretable Vector Representation of Temporal Logic](https://mlsanity.com/paper/2405.14389/) (2024)
- [Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networks](https://mlsanity.com/paper/2212.05200/) (2022)
- [Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers](https://mlsanity.com/paper/2507.07808/) (2025)
- [Scaling Learning based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout](https://mlsanity.com/paper/2403.15826/) (2024)
- [GraSP-STL: A Graph-Based Framework for Zero-Shot Signal Temporal Logic Planning via Offline Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2603.29533/) (2026)

## Abstract (arXiv)

In this paper, a method for learning a recurrent neural network (RNN) controller that maximizes the robustness of signal temporal logic (STL) specifications is presented. In contrast to previous methods, we consider synthesizing the RNN controller for which the user is able to select an STL specification arbitrarily from multiple STL specifications. To obtain such a controller, we propose a novel notion called STL2vec, which represents a vector representation of the STL specifications and exhibits their similarities. The construction of the STL2vec is useful since it allows us to enhance the efficiency and performance of the RNN controller. We validate our proposed method through the examples of the path planning problem.