Skip to Main content Skip to Navigation
Conference papers

Taylor expansion policy optimization

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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://hal.inria.fr/hal-02509561
Contributor : Michal Valko <>
Submitted on : Monday, March 16, 2020 - 9:09:45 PM
Last modification on : Wednesday, September 30, 2020 - 3:34:08 AM
Long-term archiving on: : Wednesday, June 17, 2020 - 3:17:43 PM

File

Taylor_expansion_policy_optimi...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02509561, version 1

Citation

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

Share

Metrics

Record views

94

Files downloads

322