Chapter
The Complexity of AI in the Game of Go
13:04 - 26:15 (13:11)
In the game of Go, players must combine vast amounts of human knowledge with search-based methods to solve different sub-problems. The game poses a unique challenge for AI due to its rules and symmetric nature.
Clips
The competition between AI programs for the game of Go showed that a combination of specialized systems was needed, including search-based methods and a knowledge base of billions of pieces, to create an effective AI player.
13:04 - 21:59 (08:55)
Summary
The competition between AI programs for the game of Go showed that a combination of specialized systems was needed, including search-based methods and a knowledge base of billions of pieces, to create an effective AI player. The speaker realized that instead of devoting endless hours to mastering the game, the better approach was to understand how to create an AI that could play it better than humans.
ChapterThe Complexity of AI in the Game of Go
Episode#86 – David Silver: AlphaGo, AlphaZero, and Deep Reinforcement Learning
PodcastLex Fridman Podcast
This podcast discusses the strategies involved in the game of Go, the rarity of captures, and the immense amount of knowledge and history involved in the game as well as the use of reinforcement learning.
22:00 - 26:15 (04:15)
Summary
This podcast discusses the strategies involved in the game of Go, the rarity of captures, and the immense amount of knowledge and history involved in the game as well as the use of reinforcement learning.