Properly balancing the difficulty of a video game is essential to giving players an enjoyable experience.
In a recent study, Korean scientists developed a novel dynamic difficulty adjustment method in which the player’s emotions are estimated using game data and the difficulty level is adjusted accordingly. tailored to maximize player satisfaction, Their efforts can help balance the game’s difficulty and make them more appealing to all types of gamers.
The difficulty is a difficult aspect to balance in video games. Some people like video games that offer a challenge while others like an easy experience.
Dynamic Difficulty Adjustment (DDA)
To facilitate this process, most developers use “Dynamic Difficulty Adjustment (DDA)”. The idea of DDA is to adjust the difficulty of the game in real-time based on the player’s performance. For example, if a player’s performance exceeds the developer’s expectations for a certain difficulty level, the game’s DDA may automatically increase the difficulty to increase the challenge presented to the player. While useful, this strategy is limited to only looking at the player’s performance, not how much fun they actually have.
In a recent study published in the journal Expert Systems With Applications, a research team from the Gwangju Institute of Science and Technology in South Korea decided to modify the DDA approach.
Instead of focusing on player performance, they developed DDA agents that adjust the game difficulty to maximize one of four different aspects related to player satisfaction: challenge, skill, flow, and chemotherapy.
DDA agents were trained through machine learning using data collected from real human players who played a fighting game against various artificial bits of intelligence (AIs) and then respond to a questionnaire about their experiences.
Using an algorithm called Monte Carlo tree search, each DDA agent uses real game data and simulation data to tailor the opposing AI’s fighting style to maximize a particular emotion. , or “affective state”.
Other emotion-focused methods are that it doesn’t rely on external sensors, such as electroencephalograms,” commented Associate Professor Kyung-Joong Kim, who led the study. “Once trained, our model can estimate a player’s state just by using game features.”
The team verified – through an experiment with 20 volunteers – that the proposed DDA agents can generate AIs that improve the overall experience of the players, whatever their preferences.
This is the first time affective states have been incorporated directly into DDA agents, which could be useful for commercial games. “Commercial game companies already have huge amounts of player data.
They can leverage this data to model players and solve various game balance problems using our approach,” commented Associate Professor Kim. It should be noted that this technique also has potential for other areas where it can be “gambled”, such as health, exercise, and education.
It is hoped that this research will pave the way for games where Any type of gamer, whether hardcore or casual, can enjoy!
Find Reference for the Research Paper here.
