Oppositional extension of reinforcement learning techniques

In this paper, we present different opposition schemes for four reinforcement learning methods: Q-learning, Q(λ), Sarsa, and Sarsa(λ) under assumptions that are reasonable for many real-world problems where type-II opposites generally better reflect the nature of the problem at hand. It appears that...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Information sciences 2014-08, Vol.275, p.101-114
Hauptverfasser:	Mahootchi, M., Tizhoosh, H.R., Ponnambalam, K.
Format:	Artikel
Sprache:	eng
Schlagworte:	Agglomeration Grid world Learning Management Opposition-based learning Q-learning Reinforcement Reinforcement learning Reservoir management Reservoirs Sarsa
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!