Reinforcement Learning Alphago

When Google's AI beat the world's Go champion 4-1, it stirred a certain sadness in many people. But the reality is the technologies ... We've observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through ... Become The AI Epiphany Patreon ❤️ ▻ We look at a project that I did trying to create a version of AlphaZero for the game Pente. AlphaZero uses Monte Carlo tree search ... Full episode with David Silver (Apr 2020): Clips channel (Lex Clips): ...

Multi-Agent Hide and Seek

We've observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek....

AlphaZero: An Introduction

We look at a project that I did trying to create a version of AlphaZero for the game Pente. AlphaZero uses Monte...