Completed
- Codebase, model sizes, and compute requirements
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Can Wikipedia Help Offline Reinforcement Learning - Author Interview
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - Brief paper, setup & idea recap
- 3 - Main experimental results & high standard deviations
- 4 - Why is there no clear winner?
- 5 - Why are bigger models not a lot better?
- 6 - What’s behind the name ChibiT?
- 7 - Why is iGPT underperforming?
- 8 - How are tokens distributed in Reinforcement Learning?
- 9 - What other domains could have good properties to transfer?
- 10 - A deeper dive into the models' attention patterns
- 11 - Codebase, model sizes, and compute requirements
- 12 - Scaling behavior of pre-trained models
- 13 - What did not work out in this project?
- 14 - How can people get started and where to go next?
