Training an Agent to Master a Simple Game Through Self-Play

Simulate games and predict the outcomes.

Introduction

Isn’t it amazing that everything you need to excel in a perfect information game is there for everyone to see in the rules of the game?

Unfortunately, for mere mortals like me, reading the rules of a new game is only a tiny fraction of the journey to learn to play a complex game. Most of the time is …

author computing dall dall-e dall-e 2 deep learning everything excel game games image information master reading reinforcement learning robot rules self-play simple tabula-rasa through training