A Q-learning Novelty Search Strategy for Evaluating Robustness of Deep Reinforcement Learning in Open-world Environments

Despite substantial progress in deep reinforcement learning (DRL), a systematic characterization of DRL agents' robustness to unexpected events in the environment is relatively under-studied. Such unexpected events ("novelties"), especially those that are more structural than parametr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE intelligent systems 2024-09, p.1-10
Hauptverfasser:	Islam, Shafkat, Chiu, Min-Hsueh, Bonjour, Trevor, de Oliveira, Ruy, Bhargava, Bharat, Kejriwal, Mayank
Format:	Artikel
Sprache:	eng
Schlagworte:	Deep reinforcement learning Games Heating systems Intelligent systems Monopoly Robustness Search problems Systematics Terminology Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!