General Video Game AI: Learning from Screen Capture
This work addresses the challenge of developing artificial general intelligence in the video-games domain, but it appears incremental as it builds on existing methods like DQN.
The paper tackles the problem of creating a general game-playing AI for video games by proposing a screen capture learning agent using an improved Deep Q-Network algorithm, achieving results that suggest it can learn multiple games with a single algorithm.
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.