Reinforcement Learning via an Optimization Lens

Reinforcement Learning via an Optimization Lens

Simons Institute via YouTube Direct link

Does It Matter in Practice?

11 of 21

11 of 21

Does It Matter in Practice?

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Reinforcement Learning via an Optimization Lens

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

  1. 1 Intro
  2. 2 Reinforcement karning: Learning to make decisions
  3. 3 Online vs. Offline (Batch) RL: A Basic View
  4. 4 Outline
  5. 5 Markov Decision Process (MDP)
  6. 6 MDP Example: Deterministic Shortest Path
  7. 7 More General Case: Bellman Equation
  8. 8 Bellman Operator
  9. 9 When Bellman Meets Gauss: Approximate DP
  10. 10 Divergence Example of Tsitsiklis & Van Roy (96)
  11. 11 Does It Matter in Practice?
  12. 12 A Long-standing Open Problem
  13. 13 Linear Programming Reformulation
  14. 14 Why Solving for Fixed Point Directly is Hard?
  15. 15 Addressing Difficulty #2: Legendre-Fenchel Transformation
  16. 16 Reformulation of Bellman Equation
  17. 17 Primal-dual Problems are Hard to Solve
  18. 18 A New Loss for Solving Bellman Equation
  19. 19 Eigenfunction Interpretation
  20. 20 Puddle World with Neural Networks
  21. 21 Conclusions

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.