Awesome World Models / arXiv

GenRL: Multimodal foundation world models for generalist embodied agents

作者：作者信息待提取 · 单位：IDLab, Ghent University, VERSES AI Research Lab, Mila, University of Montreal · 来源：General Approaches to World Models · 发布日期：2024 · 分类：8. World Models in the context of Model-Based RL

具身智能基础世界模型视觉语言桥接基于模型的强化学习
新标签打开 AlphaXiv新标签打开 Code
GenRL: Multimodal foundation world models for generalist embodied agents figure
AlphaXiv 中文概览（可滚动查看）