Keywords: Reinforcement Learning, Hyperparameters, Empirical Methodology
TL;DR: An empirical methodology for evaluating hyperparameter sensitivity of reinforcement learning algorithms.
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.
Primary Area: Reinforcement learning
Flagged For Ethics Review: true
Submission Number: 13872
Loading