Improving Intrinsic Exploration with Language Abstractions - Author Interview

Improving Intrinsic Exploration with Language Abstractions - Author Interview

Yannic Kilcher via YouTube Direct link

- Intro

1 of 16

1 of 16

- Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Improving Intrinsic Exploration with Language Abstractions - Author Interview

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Intro
  2. 2 - Paper Overview
  3. 3 - Aren't you just adding extra data?
  4. 4 - Why are you splitting up the AMIGo teacher?
  5. 5 - How do you train the grounding network?
  6. 6 - What about causally structured environments?
  7. 7 - Highlights of the experimental results
  8. 8 - Why is there so much variance?
  9. 9 - How much does it matter that we are testing in a video game?
  10. 10 - How does novelty interface with the goal specification?
  11. 11 - The fundamental problems of exploration
  12. 12 - Are these algorithms subject to catastrophic forgetting?
  13. 13 - What current models could bring language to other environments?
  14. 14 - What does it take in terms of hardware?
  15. 15 - What problems did you encounter during the project?
  16. 16 - Where do we go from here?

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.