Kernelized Lipschitz estimation combined with SDP yields admissible initial policies for ADP on uncertain discrete-time dynamics with probabilistic safety and closed-loop exponential stability.
Optimal and autonomous control using reinforcement learning: A survey,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Supervised and reinforcement learning are used to find initial adjoint variables for real-time solution of Hamilton-Jacobi-Bellman equations in two-point boundary value problems.
citing papers explorer
-
Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation
Kernelized Lipschitz estimation combined with SDP yields admissible initial policies for ADP on uncertain discrete-time dynamics with probabilistic safety and closed-loop exponential stability.
-
Learning-based Hamilton-Jacobi-Bellman Methods for Optimal Control
Supervised and reinforcement learning are used to find initial adjoint variables for real-time solution of Hamilton-Jacobi-Bellman equations in two-point boundary value problems.