Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation

no code implementations • 3 Jul 2019 • Ankush Chakrabarty, Devesh K. Jha, Gregery T. Buzzard, Yebin Wang, Kyriakos Vamvoudakis

We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics.

reinforcement-learning Reinforcement Learning (RL)