Minimax Optimal Adaptive Control for Systems on Cones

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Rantzer, Anders
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918221606551552
author Rantzer, Anders
author_facet Rantzer, Anders
contents The theory of optimal control on positive cones has recently identified several new problem classes where the Bellman equation can be solved explicitly, in analogy with classical linear quadratic control. In this paper, the idea is extended to minimax adaptive control, yielding exact solutions to instances of the Bellman equation for dual control. In particular, this allows for optimization of the fundamental tradeoff between exploration and exploitation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Minimax Optimal Adaptive Control for Systems on Cones
Rantzer, Anders
Optimization and Control
The theory of optimal control on positive cones has recently identified several new problem classes where the Bellman equation can be solved explicitly, in analogy with classical linear quadratic control. In this paper, the idea is extended to minimax adaptive control, yielding exact solutions to instances of the Bellman equation for dual control. In particular, this allows for optimization of the fundamental tradeoff between exploration and exploitation.
title Minimax Optimal Adaptive Control for Systems on Cones
topic Optimization and Control
url https://arxiv.org/abs/2511.22758