DQN - Playing Atari with Deep Reinforcement Learning - RL Paper Explained

DQN - Playing Atari with Deep Reinforcement Learning - RL Paper Explained

Aleksa Gordić - The AI Epiphany via YouTube Direct link

The deadly triad

8 of 13

8 of 13

The deadly triad

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. 1 High-level overview of the paper
  2. 2 Experience replay buffer
  3. 3 Difficulties with RL correlations, non-stationary distributions
  4. 4 DQN is very general
  5. 5 MDP formalism and optimal Q function
  6. 6 Function approximators
  7. 7 The loss function explained
  8. 8 The deadly triad
  9. 9 Algorithm walk-through
  10. 10 Preprocessing and architecture details
  11. 11 Additional details - normalizing score, schedule, etc.
  12. 12 Agent training metrics
  13. 13 Results

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.