---
id: 20260302-T0-16
title: "基于因果POMDP的分布偏移规划方法"
title_en: "Causal POMDP for Distribution Shift Planning"
url: https://ai.daily.yangsir.net/daily/20260302-T0-16
issue_date: 2026-03-02
publish_date: 2026-03-02T05:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2602.23545
---

# 基于因果POMDP的分布偏移规划方法

该研究提出因果部分可观测马尔可夫决策框架，用于解决实际环境中的分布偏移问题。该方法通过环境动态建模，准确捕捉状态分布变化对规划的影响。实验证明，在动态变化环境中，其规划成功率比传统方法高25%。适用于自动驾驶、机器人控制等需要适应环境变化的场景。

## English Version

**Causal POMDP for Distribution Shift Planning**

This research introduces a causal partially observable Markov decision process framework to solve distribution shift problems in real-world environments. The method captures the impact of state distribution changes on planning through environmental dynamics modeling. Experiments demonstrate 25% higher planning success rates than traditional methods in dynamic environments. It applies to autonomous driving and robot control scenarios requiring environmental adaptation.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2602.23545)

**详情页**：https://ai.daily.yangsir.net/daily/20260302-T0-16

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*