The act of remembering: a study in partially observable reinforcement learning

Reinforcement Learning (RL) agents typically learn memoryless policies---policies that only consider the last observation when selecting actions. Learning memoryless policies is efficient and optimal in fully observable environments. However, some form of memory is necessary when RL agents are faced...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-10
Hauptverfasser:	Rodrigo Toro Icarte, Valenzano, Richard, Klassen, Toryn Q, Christoffersen, Phillip, Amir-massoud Farahmand, McIlraith, Sheila A
Format:	Artikel
Sprache:	eng
Schlagworte:	Learning Policies Reagents
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!