# On Controller Tuning with Time-Varying Bayesian Optimization

arXiv: https://arxiv.org/abs/2207.11120 · HTML: https://mlsanity.com/paper/2207.11120/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning](https://mlsanity.com/paper/2108.06266/) (2021)
- [Bayesian Optimization with Safety Constraints: Safe and Automatic Parameter Tuning in Robotics](https://mlsanity.com/paper/1602.04450/) (2016)
- [Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits](https://mlsanity.com/paper/2002.02518/) (2020)
- [Time-Varying Gaussian Process Bandit Optimization](https://mlsanity.com/paper/1601.06650/) (2016)
- [Local policy search with Bayesian optimization](https://mlsanity.com/paper/2106.11899/) (2021)
- [Time-Varying Convex Optimization: Time-Structured Algorithms and Applications](https://mlsanity.com/paper/2006.08500/) (2020)
- [Automatic LQR Tuning Based on Gaussian Process Global Optimization](https://mlsanity.com/paper/1605.01950/) (2016)
- [Gaussian processes with linear operator inequality constraints](https://mlsanity.com/paper/1901.03134/) (2019)
- [Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study](https://mlsanity.com/paper/1812.06325/) (2018)
- [Hard Shape-Constrained Kernel Machines](https://mlsanity.com/paper/2005.12636/) (2020)
- [Safe and Efficient Model-free Adaptive Control via Bayesian Optimization](https://mlsanity.com/paper/2101.07825/) (2021)
- [On the Design of LQR Kernels for Efficient Controller Learning](https://mlsanity.com/paper/1709.07089/) (2017)
- [Bayesian Optimization with Shape Constraints](https://mlsanity.com/paper/1612.08915/) (2016)

## Built on by (most cited first, 13 of 13)

- [Time-Varying Gaussian Process Bandits with Unknown Prior](https://mlsanity.com/paper/2402.01632/) (2024)
- [Event-Triggered Time-Varying Bayesian Optimization](https://mlsanity.com/paper/2208.10790/) (2022)
- [Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints](https://mlsanity.com/paper/2304.06104/) (2023)
- [Local Bayesian Optimization for Controller Tuning with Crash Constraints](https://mlsanity.com/paper/2411.16267/) (2024)
- [Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes](https://mlsanity.com/paper/2405.10581/) (2024)
- [Time-Aware Latent Space Bayesian Optimization](https://mlsanity.com/paper/2603.00935/) (2026)
- [Bayesian Optimization with Structured Measurements: A Vector-Valued RKHS Framework](https://mlsanity.com/paper/2605.09775/) (2026)
- [Improving the Performance of Robust Control through Event-Triggered Learning](https://mlsanity.com/paper/2207.14252/) (2022)
- [Adaptive Bayesian Optimization for High-Precision Motion Systems](https://mlsanity.com/paper/2404.14602/) (2024)
- [Theoretical Analysis of Heteroscedastic Gaussian Processes with Posterior Distributions](https://mlsanity.com/paper/2409.12622/) (2024)
- [Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents](https://mlsanity.com/paper/2507.13491/) (2025)
- [Towards safe control parameter tuning in distributed multi-agent systems](https://mlsanity.com/paper/2508.13608/) (2025)
- [No-Regret Gaussian Process Optimization of Time-Varying Functions](https://mlsanity.com/paper/2512.00517/) (2025)

## Abstract (arXiv)

Changing conditions or environments can cause system dynamics to vary over time. To ensure optimal control performance, controllers should adapt to these changes. When the underlying cause and time of change is unknown, we need to rely on online data for this adaptation. In this paper, we will use time-varying Bayesian optimization (TVBO) to tune controllers online in changing environments using appropriate prior knowledge on the control objective and its changes. Two properties are characteristic of many online controller tuning problems: First, they exhibit incremental and lasting changes in the objective due to changes to the system dynamics, e.g., through wear and tear. Second, the optimization problem is convex in the tuning parameters. Current TVBO methods do not explicitly account for these properties, resulting in poor tuning performance and many unstable controllers through over-exploration of the parameter space. We propose a novel TVBO forgetting strategy using Uncertainty-Injection (UI), which incorporates the assumption of incremental and lasting changes. The control objective is modeled as a spatio-temporal Gaussian process (GP) with UI through a Wiener process in the temporal domain. Further, we explicitly model the convexity assumptions in the spatial dimension through GP models with linear inequality constraints. In numerical experiments, we show that our model outperforms the state-of-the-art method in TVBO, exhibiting reduced regret and fewer unstable parameter configurations.