400
v1v2 (latest)

A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning

Neural Information Processing Systems (NeurIPS), 2024
Main:9 Pages
8 Figures
Bibliography:2 Pages
3 Tables
Appendix:5 Pages
Abstract

The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achieve state-of-the-art performance reported in the literature. We currently lack a scalable and widely accepted approach to characterizing these complex interactions. This work proposes a new empirical methodology for studying, comparing, and quantifying the sensitivity of an algorithm's performance to hyperparameter tuning for a given set of environments. We then demonstrate the utility of this methodology by assessing the hyperparameter sensitivity of several commonly used normalization variants of PPO. The results suggest that several algorithmic performance improvements may, in fact, be a result of an increased reliance on hyperparameter tuning.

View on arXiv
Comments on this paper