Abstract
We provide global convergence rates for vanilla and entropy-regularized federated softmax stochastic policy gradient (FedPG) with local training. We show that FedPG converges to a near-optimal policy in terms of the average agent value, with a gap controlled by the level of heterogeneity. Remarkably, we obtain the first convergence rates for entropy-regularized policy gradient with explicit constants, leveraging a projection-like operator. Our results build upon a new analysis of federated averaging for non-convex objectives, based on the observation that the {\L}ojasiewicz-type inequalities from the single-agent setting (Mei et al., 2020) do not hold for the federated objective. This uncovers a fundamental difference between single-agent and federated reinforcement learning: while single-agent optimal policies can be deterministic, federated objectives may inherently require stochastic policies.