注册并分享邀请链接,可获得视频播放与邀请奖励。

alphaXiv
@askalphaxiv
High fidelity research
加入 November 2023
106 正在关注    61K 粉丝
New paper advised by Yann LeCun! "H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning" Most world models plan in a single latent space and at one timescale, which makes long-horizon planning expensive and forces one representation to handle both low-level motion and high-level goals. H-JEPA instead stacks JEPA world models across multiple timescales, with higher levels predicting farther into the future. The highest level first figures out roughly where the agent should go, then each lower level turns that into increasingly concrete subgoals until the bottom level outputs actual actions. On Visual AntMaze, this 3-level setup increases success from 18% to 73% while using less planner compute.
显示更多
0
13
883
114
转发到社区