# Fleet Control using Coregionalized Gaussian Process Policy Iteration

arXiv: https://arxiv.org/abs/1911.10121 · HTML: https://mlsanity.com/paper/1911.10121/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2019.

## Built on by (most cited first, 5 of 5)

- [WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control](https://mlsanity.com/paper/2501.13592/) (2025)
- [Scalable Optimization for Wind Farm Control using Coordination Graphs](https://mlsanity.com/paper/2101.07844/) (2021)
- [Non-stationary and Sparsely-correlated Multi-output Gaussian Process with Spike-and-Slab Prior](https://mlsanity.com/paper/2409.03149/) (2024)
- [TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning](https://mlsanity.com/paper/2411.19133/) (2024)
- [NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing](https://mlsanity.com/paper/2603.19864/) (2026)

## Abstract (arXiv)

In many settings, as for example wind farms, multiple machines are instantiated to perform the same task, which is called a fleet. The recent advances with respect to the Internet of Things allow control devices and/or machines to connect through cloud-based architectures in order to share information about their status and environment. Such an infrastructure allows seamless data sharing between fleet members, which could greatly improve the sample-efficiency of reinforcement learning techniques. However in practice, these machines, while almost identical in design, have small discrepancies due to production errors or degradation, preventing control algorithms to simply aggregate and employ all fleet data. We propose a novel reinforcement learning method that learns to transfer knowledge between similar fleet members and creates member-specific dynamics models for control. Our algorithm uses Gaussian processes to establish cross-member covariances. This is significantly different from standard transfer learning methods, as the focus is not on sharing information over tasks, but rather over system specifications. We demonstrate our approach on two benchmarks and a realistic wind farm setting. Our method significantly outperforms two baseline approaches, namely individual learning and joint learning where all samples are aggregated, in terms of the median and variance of the results.