arXiv:2611.13291v1 Announce Type: new Abstract: We consider the problem of approximating backward reachable and reach-avoid tubes for high-dimensional nonlinear systems whose Hamiltonians require numerical optimization over constrained controls and disturbances. Existing neural Hamilton-Jacobi (HJ) reachability methods alleviate the dimensionality bottleneck of grid-based solvers, but evaluating Hamiltonians without closed-form expressions introduces an additional computational challenge. We show that, under suitable assumptions, the gradients required for value-function training can be computed without differentiating through the inner optimization problem. Specifically, we establish an envelope-type gradient identity for the saddle point Hamiltonian, under which the optimal control and disturbance enter backpropagation as constants without gradient tracking. This enables end-to-end neural HJ reachability with numerically evaluated Hamiltonians while avoiding both solver unrolling and implicit differentiation. We demonstrate the accuracy and computational efficiency of the proposed approach on nonlinear reachability and reach-avoid problems of different scales.