Saved in:
Bibliographic Details
Main Authors: Yuan, Mingqi, Li, Bo, Jin, Xin, Zeng, Wenjun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.06101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913969019551744
author Yuan, Mingqi
Li, Bo
Jin, Xin
Zeng, Wenjun
author_facet Yuan, Mingqi
Li, Bo
Jin, Xin
Zeng, Wenjun
contents Hyperparameter optimization (HPO) is a billion-dollar problem in machine learning, which significantly impacts the training efficiency and model performance. However, achieving efficient and robust HPO in deep reinforcement learning (RL) is consistently challenging due to its high non-stationarity and computational cost. To tackle this problem, existing approaches attempt to adapt common HPO techniques (e.g., population-based training or Bayesian optimization) to the RL scenario. However, they remain sample-inefficient and computationally expensive, which cannot facilitate a wide range of applications. In this paper, we propose ULTHO, an ultra-lightweight yet powerful framework for fast HPO in deep RL within single runs. Specifically, we formulate the HPO process as a multi-armed bandit with clustered arms (MABC) and link it directly to long-term return optimization. ULTHO also provides a quantified and statistical perspective to filter the HPs efficiently. We test ULTHO on benchmarks including ALE, Procgen, MiniGrid, and PyBullet. Extensive experiments demonstrate that the ULTHO can achieve superior performance with a simple architecture, contributing to the development of advanced and automated RL systems.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
Yuan, Mingqi
Li, Bo
Jin, Xin
Zeng, Wenjun
Machine Learning
Artificial Intelligence
Hyperparameter optimization (HPO) is a billion-dollar problem in machine learning, which significantly impacts the training efficiency and model performance. However, achieving efficient and robust HPO in deep reinforcement learning (RL) is consistently challenging due to its high non-stationarity and computational cost. To tackle this problem, existing approaches attempt to adapt common HPO techniques (e.g., population-based training or Bayesian optimization) to the RL scenario. However, they remain sample-inefficient and computationally expensive, which cannot facilitate a wide range of applications. In this paper, we propose ULTHO, an ultra-lightweight yet powerful framework for fast HPO in deep RL within single runs. Specifically, we formulate the HPO process as a multi-armed bandit with clustered arms (MABC) and link it directly to long-term return optimization. ULTHO also provides a quantified and statistical perspective to filter the HPs efficiently. We test ULTHO on benchmarks including ALE, Procgen, MiniGrid, and PyBullet. Extensive experiments demonstrate that the ULTHO can achieve superior performance with a simple architecture, contributing to the development of advanced and automated RL systems.
title ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.06101