Entropy regularization has been extensively adopted to improve the efficiency, the stability, and the convergence of algorithms in reinforcement learning. This paper analyzes both quantitatively and qualitatively the impact of entropy regularization for Mean Field Game (MFG) with learning in a...

This paper studies a class of mean field games (MFGs) with singular controls of bounded velocity. By relaxing the absolute continuity of the control process, it generalizes the MFG framework of Lasry and Lions and Huang, Malhame, and Caines. It provides a unique solution to the MFG with explicit...