# Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic

arXiv: https://arxiv.org/abs/2607.08899 · HTML: https://mlsanity.com/paper/2607.08899/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Reinforcement Learning With Temporal Logic Rewards](https://mlsanity.com/paper/1612.03471/) (2016)
- [Backpropagation through Signal Temporal Logic Specifications: Infusing Logical Structure into Gradient-Based Methods](https://mlsanity.com/paper/2008.00097/) (2020)
- [Robust Online Monitoring of Signal Temporal Logic](https://mlsanity.com/paper/1506.08234/) (2015)
- [Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks](https://mlsanity.com/paper/2007.01498/) (2020)
- [Control from Signal Temporal Logic Specifications with Smooth Cumulative Quantitative Semantics](https://mlsanity.com/paper/1904.11611/) (2019)
- [Signal Temporal Logic Neural Predictive Control](https://mlsanity.com/paper/2309.05131/) (2023)
- [Control of Mobile Robots Using Barrier Functions Under Temporal Logic Specifications](https://mlsanity.com/paper/1908.04903/) (2019)
- [Sapo: Reachability Computation and Parameter Synthesis of Polynomial Dynamical Systems](https://mlsanity.com/paper/1607.02200/) (2016)
- [Fully Automated Verification of Linear Time-Invariant Systems against Signal Temporal Logic Specifications via Reachability Analysis](https://mlsanity.com/paper/2306.04089/) (2023)
- [Interval Signal Temporal Logic from Natural Inclusion Functions](https://mlsanity.com/paper/2309.10686/) (2023)
- [A temporal logic approach to modular design of synthetic biological circuits](https://mlsanity.com/paper/1306.4493/) (2013)
- [STL-based Optimization of Biomolecular Neural Networks for Regression and Control](https://mlsanity.com/paper/2509.05481/) (2025)

## Abstract (arXiv)

Signal Temporal Logic (STL) is increasingly used to describe interpretable objectives and constraints for optimal control and learning methods, especially when no target time series data is available. In this work, we propose to synthesize parameters for nonlinear systems that robustly satisfy continuous-time STL specifications for uncertain initial conditions. To this end, we use gradient-based optimization along with set-based reachability verification to efficiently learn in high-dimensional parameter spaces while providing provable satisfaction guarantees for the optimized parameters. We demonstrate the effectiveness and scalability of our method on three systems with up to 18 parameter dimensions.