Accelerated Point-Wise Maximum Approach to Approximate Dynamic Programming

Paul N. Beuchat

doi:10.1109/TAC.2021.3050440

Return

Accelerated Point-Wise Maximum Approach to Approximate Dynamic Programming

2022-01-01

Paul N. Beuchat *

Joseph Warrington

John Lygeros

DOI：10.1109/TAC.2021.3050440

Original

Save

View PDF

Abstract

En 中文

In this article, we describe an approximate dynamic programming (ADP) approach to compute lower bounds on the optimal value function for a discrete time, continuous space, and infinite horizon setting. The approach iteratively constructs a family of lower bounding approximate value functions by using the so-called Bellman inequality. The novelty of our approach is that, at each iteration, we aim to compute an approximate value function that maximizes the point-wise maximum taken with the family of approximate value functions computed thus far. This leads to a nonconvex objective, and we propose a gradient ascent algorithm to find stationary points by solving a sequence of convex optimization problems. We provide convergence guarantees for our algorithm and an interpretation for how the gradient computation relates to the state-relevance weighting parameter appearing in related ADP approaches. We demonstrate through numerical examples that, when compared to the existing approaches, the algorithm we propose computes tighter suboptimality bounds with comparable computation time.

Keywords:

Approximation algorithms

Pulse width modulation

Linear programming

Heuristic algorithms

Dynamic programming

Optimal control

Aerospace electronics

Discrete-time systems

dynamic programming

infinite horizon optimal control

stochastic systems

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.