Completed
- Value Functions and Temporal Difference Learning
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Decision Transformer - Reinforcement Learning via Sequence Modeling
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro & Overview
- 2 - Offline Reinforcement Learning
- 3 - Transformers in RL
- 4 - Value Functions and Temporal Difference Learning
- 5 - Sequence Modeling and Reward-to-go
- 6 - Why this is ideal for offline RL
- 7 - The context length problem
- 8 - Toy example: Shortest path from random walks
- 9 - Discount factors
- 10 - Experimental Results
- 11 - Do you need to know the best possible reward?
- 12 - Key-to-door toy experiment
- 13 - Comments & Conclusion
