AlphaGo - Mastering the Game of Go with Deep Neural Networks and Tree Search - RL Paper Explained

AlphaGo - Mastering the Game of Go with Deep Neural Networks and Tree Search - RL Paper Explained

Aleksa Gordić - The AI Epiphany via YouTube Direct link

Details around value network

7 of 14

7 of 14

Details around value network

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

AlphaGo - Mastering the Game of Go with Deep Neural Networks and Tree Search - RL Paper Explained

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Context behind the game of Go
  3. 3 High-level overview of components - SL policies
  4. 4 RL policy network
  5. 5 The value network
  6. 6 Going deeper
  7. 7 Details around value network
  8. 8 Understanding the search MTCS
  9. 9 Evaluation of AlphaGo
  10. 10 Older techniques
  11. 11 Even more detailed explanation of APV-MTCS
  12. 12 Virtual loss
  13. 13 Engineering
  14. 14 Neural networks and symmetries

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.