Data Augmentation for Image-Based Reinforcement Learning

Data Augmentation for Image-Based Reinforcement Learning

MIT Embodied Intelligence via YouTube Direct link

Introduction

1 of 24

1 of 24

Introduction

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Data Augmentation for Image-Based Reinforcement Learning

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

  1. 1 Introduction
  2. 2 Outline
  3. 3 Problem
  4. 4 Image Augmentation
  5. 5 Other Augmentation Strategies
  6. 6 Hyper Parameters
  7. 7 Models and Auxiliary Tasks
  8. 8 Results
  9. 9 Atari Benchmark
  10. 10 Image Augmentations
  11. 11 Summary
  12. 12 Dr Q
  13. 13 Dr Qv2
  14. 14 Dreamer
  15. 15 Conclusion
  16. 16 Reinforcement with prototypical representations
  17. 17 Limitations
  18. 18 Task Exploration
  19. 19 Selfsupervised Learning
  20. 20 ProtoRL Approach
  21. 21 Example
  22. 22 Importance of Exploration
  23. 23 Benchmarking
  24. 24 Wrapup

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.