Skip to content
← 返回课程
JHU Hands-on Robot Learning Fall 2026 · 单元 7官方资料已接入

Multitask policy learning and vision-language-action (VLA) models

日期
2026-10-15
课程资料
12 项
内容产物
0 项
视频待接入官方资源发布后会自动出现在这里

课程简介 ​

Generalization and multitask policy learning; task-conditioned diffusion policies and Large Behavior Models; language-conditioned policies and early VLAs; representing heterogeneous robot data; action tokenization (FAST, VQ-BeT, OAT) and continuous action representations; Octo and π 0 ; learning from multiple data sources with GR00T; latent actions, simulation and video-based data augmentation; catastrophic forgetting and knowledge insulation; π 0.5 and open-world generalization.
COURSE MATERIALS官方资料与延伸阅读

资料来源归原作者与课程方所有 · 笔记内容持续校订