# Safe Policy Search with Gaussian Process Models

arXiv: https://arxiv.org/abs/1712.05556 · HTML: https://mlsanity.com/paper/1712.05556/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2017.

## Built on by (most cited first, 9 of 9)

- [A Review of Safe Reinforcement Learning: Methods, Theory and Applications](https://mlsanity.com/paper/2205.10330/) (2022)
- [Enhancing LLM Safety via Constrained Direct Preference Optimization](https://mlsanity.com/paper/2403.02475/) (2024)
- [Lexicographic Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2212.13769/) (2022)
- [Constrained Reinforcement Learning with Smoothed Log Barrier Function](https://mlsanity.com/paper/2403.14508/) (2024)
- [Certification of Iterative Predictions in Bayesian Neural Networks](https://mlsanity.com/paper/2105.10134/) (2021)
- [Probabilistic Reach-Avoid for Bayesian Neural Networks](https://mlsanity.com/paper/2310.01951/) (2023)
- [Learning Robust Controllers Via Probabilistic Model-Based Policy Search](https://mlsanity.com/paper/2110.13576/) (2021)
- [Constrained Reinforcement Learning for Safe Heat Pump Control](https://mlsanity.com/paper/2409.19716/) (2024)
- [MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas](https://mlsanity.com/paper/2003.01283/) (2020)

## Abstract (arXiv)

We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our model has useful analytic properties, which allow closed form computation of error gradients and estimating the probability of violating given state space constraints. During training, as well as operation, only policies that are deemed safe are implemented on the real system, minimising the risk of failure.