Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence

1 code implementation • 8 Sep 2023 • Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He

Our main results are two-fold: (i) in the deterministic setting, we establish the first global last-iterate linear convergence result for the nested algorithm that seeks NE of zero-sum LQ games; (ii) in the model-free setting, we establish a~$\widetilde{\mathcal{O}}(\epsilon^{-2})$ sample complexity using a single-point ZO estimator.

Multi-agent Reinforcement Learning Policy Gradient Methods