HIGHLIGHTS
- who: Harrison Brown and colleagues from the (UNIVERSITY) have published the paper: World-Models for Bitrate Streaming, in the Journal: (JOURNAL)
- what: This project explores using supervised learning to construct a world-model or a learned simulator from recorded interactions. This work explores whether it is possible to build world-models for bitrate streaming, and whether world-models can provide any benefits in learning optimal policies. The authors provide experiments that show the performance of an agent trained entirely inside a learned world-model and provide sample complexity comparisons with current model-free algorithms. Instead . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.