Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality

• Published in: IDEAS Working Paper Series from RePEc
• Main Authors: Leonardos, Stefanos, Piliouras, Georgios, Spendlove, Kelly
• Format: Paper
• Language: English
• Published: St. Louis Federal Reserve Bank of St. Louis 01.01.2021

The interplay between exploration and exploitation in competitive multi-agent learning is still far from being well understood. Motivated by this, we study smooth Q-learning, a prototypical learning model that explicitly captures the balance between game rewards and exploration costs. We show that Q...