Strategizing Against Q-Learners: A Control-Theoretical Approach

In this letter, we explore the susceptibility of the independent Q-learning algorithms (a classical and widely used multi-agent reinforcement learning method) to strategic manipulation of sophisticated opponents in normal-form games played repeatedly. We quantify how much strategically sophisticated...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE control systems letters 2024, Vol.8, p.1733-1738
Hauptverfasser:	Arslantas, Yuksel, Yuceel, Ege, Sayin, Muhammed O.
Format:	Artikel
Sprache:	eng
Schlagworte:	Control theory game theory Games Heuristic algorithms Manipulator dynamics Markov processes Q-learning Reinforcement learning Stochastic processes Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!