Completed
- Measuring and balancing level difficulty
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Author Interview - ACCEL- Evolving Curricula with Regret-Based Environment Design
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - Start of interview
- 3 - How did you get into this field?
- 4 - What is minimax regret?
- 5 - What levels does the regret objective select?
- 6 - Positive value loss correcting my mistakes
- 7 - Why is the teacher not learned?
- 8 - How much domain-specific knowledge is needed?
- 9 - What problems is this applicable to?
- 10 - Single agent vs population of agents
- 11 - Measuring and balancing level difficulty
- 12 - How does generalization emerge?
- 13 - Diving deeper into the experimental results
- 14 - What are the unsolved challenges in the field?
- 15 - Where do we go from here?
