Taylor expansion policy optimization - Archive ouverte HAL Access content directly
Conference Papers Year :

Taylor expansion policy optimization

(1, 2) , (2) , (2)
1
2
Michal Valko
Rémi Munos
  • Function : Author
  • PersonId : 836863

Abstract

In this work, we investigate the application of Taylor expansions in reinforcement learning. In particular, we propose Taylor expansion policy optimization , a policy optimization formalism that generalizes prior work (e.g., TRPO) as a first-order special case. We also show that Taylor expansions intimately relate to off-policy evaluation. Finally, we show that this new formulation entails modifications which improve the performance of several state-of-the-art distributed algorithms.
Fichier principal
Vignette du fichier
Taylor_expansion_policy_optimization__arxiv_ (3).pdf (765.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02509561 , version 1 (16-03-2020)

Identifiers

  • HAL Id : hal-02509561 , version 1

Cite

Yunhao Tang, Michal Valko, Rémi Munos. Taylor expansion policy optimization. International Conference on Machine Learning, 2020, Vienna, Austria. ⟨hal-02509561⟩
60 View
104 Download

Share

Gmail Facebook Twitter LinkedIn More