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