Generalization and Robustness in Offline Reinforcement Learning

Generalization and Robustness in Offline Reinforcement Learning

Simons Institute via YouTube Direct link

Intro

1 of 19

1 of 19

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Generalization and Robustness in Offline Reinforcement Learning

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

  1. 1 Intro
  2. 2 Empirical RL for large-scale problems
  3. 3 Traditional Online RL paradigm
  4. 4 offline RL paradigm
  5. 5 Potential Applications of Offline RL
  6. 6 Why offline RL is challenging?
  7. 7 Finite Horizon MDPs
  8. 8 Offline Data Collection
  9. 9 Offline Data Coverage
  10. 10 Learning goal in Offline RL: Robustness
  11. 11 Learning goal in Offline RL: Generalization
  12. 12 A Model-based Approach
  13. 13 A Naive Model-based Approach
  14. 14 Formal Theoretical Guarantee for CPPO
  15. 15 Traditional Imitation Learning
  16. 16 Covariate shift in Imitation
  17. 17 Offline Imitation Learning
  18. 18 Explanation of MILO
  19. 19 Experiments of MILO

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.