NEW YORK: US researchers have developed an artificial intelligence (AI) software that is better at predicting what goal a player is trying to achieve in a video game.
The advance holds promise for helping game developers design new ways of improving the gameplay experience for players.
"We developed this software for use in educational gaming, but it has applications for all video game developers," said Dr James Lester, a professor of computer science at the North Carolina (NC) State University.
This is a key step in developing player adaptive games that can respond to player actions to improve the gaming experience, either for entertainment or education.
The researchers used 'deep learning' to develop the AI software.
Deep learning is a family of machine learning techniques that can extrapolate patterns from large collections of data and make predictions. To test the AI programme, researchers turned to an educational game called 'Crystal Island.'
They amassed logs of player behaviour (tracking every action a player took in the game) for 137 different players.
They were able to test the predictive AI software against the 'Crystal Island' player logs to determine its accuracy in goal recognition.
"For games, the current state of the art AI programme for goal recognition has an accuracy rate of 48.4%. The accuracy rate for our new programme is 62.3%. That is a big jump," informed co-author Wookhee Min from NC State.
The paper will be presented at the 10th annual conference on artificial intelligence and interactive digital entertainment in Raleigh, North Carolina, Oct 5-7.
The advance holds promise for helping game developers design new ways of improving the gameplay experience for players.
"We developed this software for use in educational gaming, but it has applications for all video game developers," said Dr James Lester, a professor of computer science at the North Carolina (NC) State University.
This is a key step in developing player adaptive games that can respond to player actions to improve the gaming experience, either for entertainment or education.
The researchers used 'deep learning' to develop the AI software.
Deep learning is a family of machine learning techniques that can extrapolate patterns from large collections of data and make predictions. To test the AI programme, researchers turned to an educational game called 'Crystal Island.'
They amassed logs of player behaviour (tracking every action a player took in the game) for 137 different players.
They were able to test the predictive AI software against the 'Crystal Island' player logs to determine its accuracy in goal recognition.
"For games, the current state of the art AI programme for goal recognition has an accuracy rate of 48.4%. The accuracy rate for our new programme is 62.3%. That is a big jump," informed co-author Wookhee Min from NC State.
The paper will be presented at the 10th annual conference on artificial intelligence and interactive digital entertainment in Raleigh, North Carolina, Oct 5-7.
0 Comments