VIS Lab
VIS Lab
People
Publications
Contact
Light
Dark
Automatic
World models
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approaches to intrinsic motivation that follow general principles such as …
Cite
×