Policy search in continuous action domains: An overview - Sorbonne Université Accéder directement au contenu
Article Dans Une Revue Neural Networks Année : 2019

Policy search in continuous action domains: An overview

Résumé

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.
Fichier principal
Vignette du fichier
1803.04706.pdf (741.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02182466 , version 1 (12-07-2019)

Identifiants

Citer

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

Altmetric

Partager

Gmail Facebook X LinkedIn More