A travel-cost value function defined via a proposed running cost is the unique bounded viscosity solution to a time-dependent HJB PDE whose negative sublevel set is the strict backward-reachable tube, and small-step RL value iteration converges to the forward discounted HJB solution.
Springer, 1997
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.SY 2years
2026 2representative citing papers
Develops verifiable error bounds for PINN solutions of Lyapunov and HJB PDEs that turn residual bounds into relative error bounds, certified value function bounds, and valid Lyapunov functions.
citing papers explorer
-
Unifying Hamilton-Jacobi Reachability and Reinforcement Learning
A travel-cost value function defined via a proposed running cost is the unique bounded viscosity solution to a time-dependent HJB PDE whose negative sublevel set is the strict backward-reachable tube, and small-step RL value iteration converges to the forward discounted HJB solution.
-
Verifiable Error Bounds for Physics-Informed Neural Network Solutions of Lyapunov and Hamilton-Jacobi-Bellman Equations
Develops verifiable error bounds for PINN solutions of Lyapunov and HJB PDEs that turn residual bounds into relative error bounds, certified value function bounds, and valid Lyapunov functions.