# Deep Reinforcement Learning using Cyclical Learning Rates

arXiv: https://arxiv.org/abs/2008.01171 · HTML: https://mlsanity.com/paper/2008.01171/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning](https://mlsanity.com/paper/2409.18827/) (2024)
- [Regime-Switching Langevin Monte Carlo Algorithms](https://mlsanity.com/paper/2509.00941/) (2025)
- [Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize](https://mlsanity.com/paper/2302.05516/) (2023)
- [A Deep Reinforcement Learning Trader without Offline Training](https://mlsanity.com/paper/2303.00356/) (2023)
- [Exploration of Hepatitis B Virus Infection Dynamics through Physics-Informed Deep Learning Approach](https://mlsanity.com/paper/2503.10708/) (2025)
- [Autonomous Vehicle Lateral Control Using Deep Reinforcement Learning with MPC-PID Demonstration](https://mlsanity.com/paper/2506.04040/) (2025)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gradient descent (SGD) is the learning rate. We investigate cyclical learning and propose a method for defining a general cyclical learning rate for various DRL problems. In this paper we present a method for cyclical learning applied to complex DRL problems. Our experiments show that, utilizing cyclical learning achieves similar or even better results than highly tuned fixed learning rates. This paper presents the first application of cyclical learning rates in DRL settings and is a step towards overcoming manual hyperparameter tuning.