Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation

2019/07/03 by Chakrabarty, Ankush, Jha, Devesh K., Buzzard, Gregery T. +2
#Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1907.02151

Abstract

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. We employ kernelized Lipschitz estimation and semidefinite programming for computing admissible initial control policies with provably high probability. Such admissible controllers enable safe initialization and constraint enforcement while providing exponential stability of the equilibrium of the closed-loop system.

Related

• Approximate Dynamic Programming For Linear Systems with State and Input Constraints
• Lagrangian-based online safe reinforcement learning for state-constrained systems
• A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming
• Safe Model-Based Reinforcement Learning for Systems with Parametric Uncertainties
• Feasible Policy Iteration for Safe Reinforcement Learning