UCB Momentum Q-learning: Correcting the bias without forgetting

We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stage-dependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add a momentum term and rely on the principle of optimism in face of uncertainty t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-03
Hauptverfasser:	Menard, Pierre, Omar Darwiche Domingues, Shang, Xuedong, Valko, Michal
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Bias Decision theory Lower bounds Machine learning Markov processes Momentum
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!