Language Models as Zero-Shot Planners - Extracting Actionable Knowledge for Embodied Agents

Language Models as Zero-Shot Planners - Extracting Actionable Knowledge for Embodied Agents

Yannic Kilcher via YouTube Direct link

- Contributions of this paper

4 of 12

4 of 12

- Contributions of this paper

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Language Models as Zero-Shot Planners - Extracting Actionable Knowledge for Embodied Agents

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

  1. 1 - Intro & Overview
  2. 2 - The VirtualHome environment
  3. 3 - The problem of plan evaluation
  4. 4 - Contributions of this paper
  5. 5 - Start of interview
  6. 6 - How to use language models with environments?
  7. 7 - What does model size matter?
  8. 8 - How to fix the large models' outputs?
  9. 9 - Possible improvements to the translation procedure
  10. 10 - Why does Codex perform so well?
  11. 11 - Diving into experimental results
  12. 12 - Future outlook

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.