We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We first consider this problem under a certain scaling of the approximating function, leading to a regime called lazy training. In this regime, the parameters of the model vary only slightly during the learning process, a feature that has recently been observed in the training of neural networks, where the scaling we study arises naturally, implicit in the initialization of their parameters. Both in the under- and over-parametrized frameworks, we prove exponential convergence to local, respectively global minimizers of the above algorithm in the lazy training regime. We then compare this scaling of the parameters to the mean-field regime, where the approximately linear behavior of the model is lost. Under this alternative scaling we prove that all fixed points of the dynamics in parameter space are global minimizers. We finally give examples of our convergence results in the case of models that diverge if trained with non-lazy TD learning, and in the case of neural networks.
View on arXiv