Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation

In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms, projection-free and max-norm regularized Neural TD learning, and establish the first convergence bounds for these algorithms. An interesting observation from our results is that max-norm regularization can dramatically improve the performance of TD learning algorithms, both in terms of sample complexity and overparameterization. In particular, we prove that max-norm regularization appears to be more effective than $\ell_2$-regularization, again both in terms of sample complexity and overparameterization. The results in this work rely on a novel Lyapunov drift analysis of the network parameters as a stopped and controlled random process.