# General Video Game AI: Learning from Screen Capture

## TL;DR

This paper introduces a novel screen capture learning agent for General Video Game AI, utilizing an improved Deep Q-Network to learn multiple games with a single algorithm, advancing general game playing research.

## Contribution

It is the first to develop a screen capture learning agent within the General Video Game AI framework using an enhanced Deep Q-Network.

## Key findings

- The agent successfully learned to play various games.
- The approach demonstrates potential for general game learning.
- Single algorithm adapts to multiple game categories.

## Abstract

General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain. In this paper, we propose for the first time a screen capture learning agent for General Video Game AI framework. A Deep Q-Network algorithm was applied and improved to develop an agent capable of learning to play different games in the framework. After testing this algorithm using various games of different categories and difficulty levels, the results suggest that our proposed screen capture learning agent has the potential to learn many different games using only a single learning algorithm.