---
title: "Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.02809v1"
permalink: "https://feed.astralor.com/items/itm_3079108db5c34a09b56333fc"
published: "2026-11-02T09:17:21.000Z"
score: 55
channel: "ai"
tags: ["Offline Approximate Value","Iteration","Reinforcement Learning Approach","Satellite Constellation Deployment","Walker-type"]
---

# Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment

## 速览

This paper introduces a reinforcement learning-based approximate dynamic programming approach to optimize the deployment of Walker-type satellite constellations under uncertainties, including launch failures and satelli…

## 关键点

- This paper introduces a reinforcement learning-based approximate dynamic programming approach to optimize the deployment of Walker-type satellite constellations under uncertainties, including launch failures and satelli…
- We formulate the problem as a Markov Decision Process that incorporates low-injection orbit launches, continuous low-thrust orbit raising, and variable satellite loads.
- We adopt the offline approximate value iteration solution method, using linear function approximation with basis functions and action pruning strategies to substantially reduce the computational and memory requirements …

## 全文

This paper introduces a reinforcement learning-based approximate dynamic programming approach to optimize the deployment of Walker-type satellite constellations under uncertainties, including launch failures and satellite malfunctions. We formulate the problem as a Markov Decision Process that incorporates low-injection orbit launches, continuous low-thrust orbit raising, and variable satellite loads. We adopt the offline approximate value iteration solution method, using linear function approximation with basis functions and action pruning strategies to substantially reduce the computational and memory requirements for finding optimal decision policies. Preliminary results demonstrate convergence to policies with low expected costs and deployment times, both of which are lower than those of a rolling-horizon baseline, showcasing a novel application of approximate dynamic programming in space logistics.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3079108db5c34a09b56333fc