Skip to Main content Skip to Navigation
Conference papers

Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning

Abstract : Recent Reinforcement Learning (RL) algorithms making use of Kullback-Leibler (KL) regularization as a core component have shown outstanding performance. Yet, only little is understood theoretically about why KL regularization helps, so far. We study KL regularization within an approximate value iteration scheme and show that it implicitly averages q-values. Leveraging this insight, we provide a very strong performance bound, the very first to combine two desirable aspects: a linear dependency to the horizon (instead of quadratic) and an error propagation term involving an averaging effect of the estimation errors (instead of an accumulation effect). We also study the more general case of an additional entropy regularizer. The resulting abstract scheme encompasses many existing RL algorithms. Some of our assumptions do not hold with neural networks, so we complement this theoretical analysis with an extensive empirical study.
Complete list of metadata
Contributor : Bruno Scherrer Connect in order to contact the contributor
Submitted on : Wednesday, February 10, 2021 - 1:40:07 PM
Last modification on : Wednesday, November 3, 2021 - 7:09:46 AM
Long-term archiving on: : Tuesday, May 11, 2021 - 6:36:47 PM


Files produced by the author(s)


  • HAL Id : hal-03137351, version 1



Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, et al.. Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning. NeurIPS - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Online, Canada. ⟨hal-03137351⟩



Les métriques sont temporairement indisponibles