Completed
Function approximators
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
DQN - Playing Atari with Deep Reinforcement Learning - RL Paper Explained
Automatically move to the next video in the Classroom when playback concludes
- 1 High-level overview of the paper
- 2 Experience replay buffer
- 3 Difficulties with RL correlations, non-stationary distributions
- 4 DQN is very general
- 5 MDP formalism and optimal Q function
- 6 Function approximators
- 7 The loss function explained
- 8 The deadly triad
- 9 Algorithm walk-through
- 10 Preprocessing and architecture details
- 11 Additional details - normalizing score, schedule, etc.
- 12 Agent training metrics
- 13 Results
