Главная
Study mode:
on
1
Intro
2
AlphaGo
3
AlphaZero
4
Chess
5
Shogi
6
Deep Blue
7
Search Space
8
Minimax Search
9
handcrafted features
10
point valuations
11
opening books endgame tables
12
AlphaZero approach
13
Training of policy improvement
14
Deep Neural Network
15
Architecture
16
Inputs and outputs
17
Features
18
Research
19
Differences from AlphaGo
20
Statistics
21
Results
22
Training Times
23
Conclusion
24
Chess Agents
25
Hikaru Nakamura
Description:
Explore the groundbreaking advancements in artificial intelligence for chess and shogi in this 25-minute lecture by Kira Selby. Delve into the evolution of AI in board games, from Deep Blue to AlphaGo and AlphaZero. Examine the traditional approaches of minimax search, handcrafted features, and opening books, then contrast them with AlphaZero's revolutionary deep neural network architecture. Understand the training process, policy improvement, and the unique features that set AlphaZero apart from its predecessors. Analyze the impressive statistics and results, including training times and performance against top human players like Hikaru Nakamura. Gain insights into the future of AI in complex strategy games and its potential applications beyond the board.

Mastering Chess and Shogi

Pascal Poupart
Add to list
0:00 / 0:00