Главная
Study mode:
on
1
- AlphaGo lineage of agents
2
- Comparing AlphaGo Zero with AlphaGo
3
- High-level explanation of AlphaGo Zero inner workings
4
- MCTS recap
5
- Training details and curves
6
- Architecture impact
7
- Knowledge acquired
8
- Results
9
- Discovering joseki
10
- Human domain knowledge in AlphaGo Zero
11
- Pipeline overview
12
- Self-play thread explained
13
- Further details PUCT recap, etc.
14
- AlphaZero what's new?
Description:
Dive into a comprehensive video lecture exploring DeepMind's groundbreaking AI agents AlphaGo Zero and AlphaZero. Learn how these revolutionary algorithms mastered complex games like Go, Chess, and Shogi through pure self-play, without any human knowledge input. Explore the inner workings of these AI systems, including their architecture, training process, and the knowledge they acquired. Understand key concepts like Monte Carlo Tree Search (MCTS), self-play mechanisms, and the impact of architectural choices. Discover how these AI agents surpassed human expertise, even uncovering new strategies in ancient games. Compare AlphaGo Zero with its predecessors and examine the innovations introduced in AlphaZero. Gain insights into the future of AI and its potential applications beyond game-playing.

DeepMind's AlphaGo Zero and AlphaZero - RL Paper Explained

Aleksa Gordić - The AI Epiphany
Add to list
0:00 / 0:00