Preprint
Nov 2026
Bridging Neural Tangent Kernel Analysis and Reinforcement Learning for Deep Function Approximation
This work extends the NTK framework to reinforcement learning (RL) by introducing a temporal-difference flow formulation that accommodates time-varying mini-batches and TD targets, yielding a closed-form solution for value function evolution in an overparametrized setting.
William St-Arnaud, Margarida Carvalho, Golnoosh Farnadi
· 0 citations