# A Hierarchical Two-tier Approach to Hyper-parameter Optimization in Reinforcement Learning

arXiv: https://arxiv.org/abs/1909.08332 · HTML: https://mlsanity.com/paper/1909.08332/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2019.

## Built on by (most cited first, 1 of 1)

- [ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning](https://mlsanity.com/paper/2503.06101/) (2025)

## Abstract (arXiv)

Optimization of hyper-parameters in reinforcement learning (RL) algorithms is a key task, because they determine how the agent will learn its policy by interacting with its environment, and thus what data is gathered. In this work, an approach that uses Bayesian optimization to perform a two-step optimization is proposed: first, categorical RL structure hyper-parameters are taken as binary variables and optimized with an acquisition function tailored for such variables. Then, at a lower level of abstraction, solution-level hyper-parameters are optimized by resorting to the expected improvement acquisition function, while using the best categorical hyper-parameters found in the optimization at the upper-level of abstraction. This two-tier approach is validated in a simulated control task. Results obtained are promising and open the way for more user-independent applications of reinforcement learning.