The right game for the right player
Problem being addressed
Methods for dynamic difficulty adjustment allow games to be tailored to particular players to maximize their engagement. However, current methods often only modify a limited set of game features such as the difficulty of the opponents, or the availability of resources.
A novel model that generates and searches for complete levels with a specific target difficulty in only a few trials. This advance is enabled by through an Intelligent Trial-and-Error algorithm, originally developed to allow robots to adapt quickly. The algorithm first creates a large variety of different levels that vary across predefined dimensions such as leniency or map coverage; then the difficulty of the prior map is updated to reflect the ability of the agent.
Advantages of this solution
The approach can reliably find levels with a specific target difficulty for a variety of planning agents in only a few trials, while maintaining an understanding of their skill landscape.
Solution originally applied in these industries
Possible New Application of the Work
The suggested method can be successfully used in educational purposes, especially for the subjects like mathematics or physics, to identify the lever of each student and adjust the assignments, their amount and difficulty for better and easier understanding.
The method can be used in rehabilitation process to measure the patient's progress and adjust the level of exercise intensity; rehabilitation after brain trauma would be a great example.
Source URL: #############