Mixtures of Experts Unlock Parameter Scaling for Deep RL
Johan Samir Obando Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob Nicolaus Foerster, Gintare Karolina Dziugaite, Doina Precup
Abstract
The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, however, where increasing the parameter count of a model often hurts its final performance. In this paper, we demonstrate that incorporating Mixture-of-Expert (MoE) modules, and in particular Soft MoEs (Puigcerver et al., 2023), into value-based networks results in more parameter-scalable models, evidenced by substantial performance increases across a variety of training regimes and model sizes. This work thus provides strong empirical evidence towards developing scaling laws for reinforcement learning.
BibTeX
@inproceedings{
ceron2024mixtures,
title={Mixtures of Experts Unlock Parameter Scaling for Deep {RL}},
author={Johan Samir Obando Ceron and Ghada Sokar and Timon Willi and Clare Lyle and Jesse Farebrother and Jakob Nicolaus Foerster and Gintare Karolina Dziugaite and Doina Precup and Pablo Samuel Castro},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=X9VMhfFxwn}
}