Skip to yearly menu bar Skip to main content


Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime

James-Michael Leahy · Bekzhan Kerimkulov · David Siska · Lukasz Szpruch

Hall E #902

Keywords: [ T: Reinforcement Learning and Planning ] [ RL: Function Approximation ] [ T: Probabilistic Methods ] [ RL: Policy Search ] [ RL: Continuous Action ] [ RL: Discounted Cost/Reward ] [ Reinforcement Learning ]


We study the global convergence of policy gradient for infinite-horizon, continuous state and action space, and entropy-regularized Markov decision processes (MDPs). We consider a softmax policy with (one-hidden layer) neural network approximation in a mean-field regime. Additional entropic regularization in the associated mean-field probability measure is added, and the corresponding gradient flow is studied in the 2-Wasserstein metric. We show that the objective function is increasing along the gradient flow.Further, we prove that if the regularization in terms of the mean-field measure is sufficient, the gradient flow converges exponentially fast to the unique stationary solution, which is the unique maximizer of the regularized MDP objective. Lastly, we study the sensitivity of the value function along the gradient flow with respect to regularization parameters and the initial condition. Our results rely on the careful analysis of the non-linear Fokker--Planck--Kolmogorov equation and extend the pioneering work of \cite{mei2020global} and \cite{agarwal2020optimality}, which quantify the global convergence rate of policy gradient for entropy-regularized MDPs in the tabular setting.

Chat is not available.