---
id: 20260510-T0-05
title: "无需手动设定任务规则，LANTERN让强化学习迁移更快更准"
title_en: "LANTERN Automates Transfer Learning in RL Without Manual Task Automata"
url: https://ai.daily.yangsir.net/daily/20260510-T0-05
issue_date: 2026-05-10
publish_date: 2026-05-09T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2605.05478
---

# 无需手动设定任务规则，LANTERN让强化学习迁移更快更准

强化学习中的迁移学习旨在利用已有知识加速新任务的学习。然而，现有神经符号迁移方法严重依赖人工设定的任务自动机，且多假设单一源任务，极大地限制了灵活性。LANTERN提出一种由LLM增强的神经符号迁移框架，通过经验门控推理网络自动提取和迁移规则。该方法免去了手动编写规则的繁琐步骤，让强化学习智能体在陌生环境中的训练速度大幅提升。

## English Version

**LANTERN Automates Transfer Learning in RL Without Manual Task Automata**

Transfer learning in reinforcement learning (RL) aims to accelerate new task learning using prior knowledge. However, existing neurosymbolic methods rely heavily on manually specified task automata and single-source assumptions, limiting flexibility. LANTERN introduces an LLM-augmented framework using experience-gated reasoning networks to automate rule extraction and transfer, eliminating manual setup and significantly boosting training speed in unfamiliar environments.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2605.05478)

**详情页**：https://ai.daily.yangsir.net/daily/20260510-T0-05

---

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