Reproducible, Reusable, and Robust Reinforcement Learning - Joelle Pineau

Reproducible, Reusable, and Robust Reinforcement Learning - Joelle Pineau

Institute for Advanced Study via YouTube Direct link

Intro

1 of 23

1 of 23

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Reproducible, Reusable, and Robust Reinforcement Learning - Joelle Pineau

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

  1. 1 Intro
  2. 2 Reproducibility refers to the ability of a researcher to duplicate the results of a prior study....
  3. 3 Reproducibility crisis in science (2016)
  4. 4 Reinforcement learning (RL)
  5. 5 Adaptive neurostimulation
  6. 6 RL via Policy gradient methods
  7. 7 Policy gradient papers
  8. 8 Policy gradient baseline algorithms
  9. 9 Robustness of policy gradient algorithms
  10. 10 Codebase comparison
  11. 11 An intricate interplay of hyperparameters!
  12. 12 Fair comparison is easy, right?
  13. 13 How should we measure performance of the learned policy?
  14. 14 From fair comparisons...
  15. 15 How about a reproducibility checklist?
  16. 16 The role of infrastructure on reproducibility
  17. 17 Myth or fact?
  18. 18 Generalization in RL
  19. 19 Natural world has incredible complexity!
  20. 20 Natural world = RL simulation
  21. 21 Real-world video = RL simulation
  22. 22 Step out into the real-world!
  23. 23 ICLR Reproducibility Challenge Second Edition, 2019

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.