Name
Abstract | ||
|---|---|---|
In this paper, we present a dynamic adaptation framework to adapt the game scenarios for a multi-agent training game. We consider the problem where a trainee has to practice along multiple objectives during the training, and each objective is assigned with a desired difficulty level. The proposed dynamic adaptation approach takes into account of individual player's playing ability as well as the dynamic game circumstance to determine how to adapt the game scenario. We utilize artificial neural networks to construct a data-driven prediction model to estimate the effect of taking certain adaptation to the game. Based on the prediction model, our adaptation framework can determine both the direction and quantity of the adaptation. The performance of the proposed framework is testified in a food distribution training game and the results demonstrate the effectiveness of our adaptation framework. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/WI-IAT.2015.79 | WI-IAT |
Keywords | Field | DocType |
Multi-agent games, Online adaptivity, Emotion modeling, Procedural content | Data-driven,Computer science,Feature extraction,Artificial intelligence,Sequential game,Artificial neural network,Dynamic priority scheduling,Machine learning | Conference |
Volume | Citations | PageRank |
2 | 0 | 0.34 |
References | Authors | |
9 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Haiyan Yin | 1 | 54 | 5.71 |
| Linbo Luo | 2 | 53 | 7.54 |
| Wentong Cai | 3 | 1928 | 197.81 |
| Jing-hui Zhong | 4 | 380 | 33.00 |