Главная
Study mode:
on
1
Intro
2
Context behind the game of Go
3
High-level overview of components - SL policies
4
RL policy network
5
The value network
6
Going deeper
7
Details around value network
8
Understanding the search MTCS
9
Evaluation of AlphaGo
10
Older techniques
11
Even more detailed explanation of APV-MTCS
12
Virtual loss
13
Engineering
14
Neural networks and symmetries
Description:
Dive into a comprehensive video explanation of the groundbreaking AlphaGo paper, which details the first AI system to defeat a professional Go player. Explore the intricate components of AlphaGo, including supervised learning policies, reinforcement learning networks, and value networks. Gain a deep understanding of Monte Carlo Tree Search (MCTS) and its application in AlphaGo. Learn about the evaluation process, older techniques, and engineering aspects behind this revolutionary AI system. Discover how neural networks and symmetries play a crucial role in AlphaGo's success, and grasp the context of why conquering the game of Go was considered a significant milestone in artificial intelligence.

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

Aleksa Gordić - The AI Epiphany
Add to list