Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments

Cédric Colas 1 Olivier Sigaud 2, 1 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called "reproducibility crisis" in deep reinforcement learning. In this tutorial paper, we explain how the number of random seeds relates to the probabilities of statistical errors. For both the t-test and the bootstrap confidence interval test, we recall theoretical guidelines to determine the number of random seeds one should use to provide a statistically significant comparison of the performance of two algorithms. Finally, we discuss the influence of deviations from the assumptions usually made by statistical tests. We show that they can lead to inaccurate evaluations of statistical errors and provide guidelines to counter these negative effects. We make our code available to perform the tests 1 .
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-01890154
Contributor : Cédric Colas <>
Submitted on : Monday, October 8, 2018 - 1:38:07 PM
Last modification on : Thursday, March 18, 2021 - 1:36:01 PM
Long-term archiving on: : Wednesday, January 9, 2019 - 2:21:15 PM

File

1806.08295.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01890154, version 1

Citation

Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer. How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments. 2018. ⟨hal-01890154⟩

Share

Metrics

Record views

154

Files downloads

367