用抽象地图实现零样本迷宫导航，像读地图一样智能行进
Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps
- 基于地图生成网络权重，实现跨布局快速适应
- 在未见过的迷宫中零样本导航成功率显著提升
- 适合需要泛化能力的机器人路径规划场景
学习在不同环境中导航是决策领域的长期挑战。本文聚焦于使用给定的二维抽象俯视地图实现零样本导航。如同人类阅读纸质地图导航，该智能体在学习一系列训练地图后，可将新布局的地图作为图像输入进行导航。我们提出一种基于模型的强化学习方法，联合学习一个超模型，其以俯视地图为输入，预测转移网络的权重。实验采用DeepMind Lab环境，并使用生成地图定制布局。所提方法在零样本条件下对新环境的适应能力更强，且对噪声更具鲁棒性。
原文摘要 · Abstract (English)
Learning navigation capabilities in different environments has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability using given abstract $2$-D top-down maps. Like human navigation by reading a paper map, the agent reads the map as an image when navigating in a novel layout, after learning to navigate on a set of training maps. We propose a model-based reinforcement learning approach for this multi-task learning problem, where it jointly learns a hypermodel that takes top-down maps as input and predicts the weights of the transition network. We use the DeepMind Lab environment and customize layouts using generated maps. Our method can adapt better to novel environments in zero-shot and is more robust to noise.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。