Mon. Oct 3rd, 2022

Are you going to get well and feel fine? Or maybe you’re really tired? Irritable and frustrated? Perhaps sad and melancholy? In order to find out many different games, video games might help you adjust your difficulty as well as how the player feels. Because it may not be too bad for you to feel angry at a game.


Scientists have devised a quite interesting way for such a thing in South Korea. The researchers developed a dynamic difficulty model that would suit the players’ personalities and improve the player’s performance in order to maximize satisfaction. Because who likes to get maximum satisfaction?

Related: Fighting Games Are Only Satisfying When You Look For Winning.

The developers know many times about the balance needed to play on the pitch and playtime. Although settings can be changed, it often requires the player to change the settings manually. The Korean scientists propose a lot more dynamic.

A simulator, by which the players gather data, then adjust their difficulty in order to maximize one of four different aspects about a player’s satisfaction: challenge, competence, flow and valence.

The scientists used a simulation technique to train their DDA agents, and the human players played the fighting game against AI opponents to generate a data stream, and the human were also forced to answer the questionnaire about their experience. With an algorithm called Monte-Carlo tree search, each DDA agent uses real game data and simulation data to tune and tweak the opposing AI’s fighting style in an effort to maximize a specific emotion and “affective state”.

The professor said that their approach benefited their approach because the player doesn’t need external sensors to detect their emotions. “When we first learn, our model uses an in-game feature to evaluate the player’s progress,” she said.

The study was small, with only 20 volunteers, but the team said that the DDA agents produced AIs that improved player’s entire experienc. The author of fighting games is responding only to the most direct response. The question is how it can be used for other sports, but the professor replied.

“Comercial game companies already have huge amounts of player data. They can utilize these data to model the players and solve various problems relating to game balancing using our approach,” said Kim.

The paper titled “Diversifying Dynamic Adapters by integrating player state models into Monte-Carlo tree search” will be published in the journal Expert Systems With Applications on November 1. Not only are you interested in buying something, but it’s already available online now and can be found here.

Source link

By anupam

Leave a Reply

Your email address will not be published.