Skip to Main content Skip to Navigation
Journal articles

Policy search in continuous action domains: An overview

Abstract : Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary algorithms. In this paper, we present a broad survey of policy search methods, providing a unified perspective on very different approaches, including also Bayesian Optimization and directed exploration methods. The main message of this overview is in the relationship between the families of methods, but we also outline some factors underlying sample efficiency properties of the various approaches.
Document type :
Journal articles
Complete list of metadata

Cited literature [128 references]  Display  Hide  Download

https://hal.sorbonne-universite.fr/hal-02182466
Contributor : Gestionnaire Hal-Su <>
Submitted on : Friday, July 12, 2019 - 5:26:05 PM
Last modification on : Wednesday, May 19, 2021 - 11:58:14 AM

File

1803.04706.pdf
Files produced by the author(s)

Identifiers

Citation

Olivier Sigaud, Freek Stulp. Policy search in continuous action domains: An overview. Neural Networks, Elsevier, 2019, 113, pp.28-40. ⟨10.1016/j.neunet.2019.01.011⟩. ⟨hal-02182466⟩

Share

Metrics

Record views

79

Files downloads

317