Multi-agent Learning Dynamics: A Survey

Abstract. In this paper we compare state-of-the-art multi-agent reinforcement learning algorithms in a wide variety of games. We consider two types of algorithms: value iteration and policy iteration. Four characteristics are studied: initial conditions, parameter settings, convergence speed, and local versus global convergence. Global convergence is still difficult to achieve in practice, despite existing theoretical guarantees. Multiple visualizations are included to provide a comprehensive insight into the learning dynamics.

• Type: Conference
• Year: 2007
• Where: CIA
• Authors: H. Jaap van den Herik, Daniel Hennes, Michael Kaisers, Karl Tuyls, Katja Verbeeck
• Keywords: Artificial Intelligence, CIA 2007, Global Convergence, Reinforcement Learning Algorithms, Versus Global Convergence