Loading...
Please wait, while we are loading the content...
Similar Documents
Investigation of Various Online Adaptation Methods of Computer-Game AI Rulebase in Dynamic Scripting
| Content Provider | Semantic Scholar |
|---|---|
| Copyright Year | 2007 |
| Abstract | In this paper, we investigate various online adaptation methods of computer-game AI rulebase in a technique called Dynamic Scripting (DS). DS is a technique for balancing the level of computer controlled characters that play computer games against human players. It online updates rule weights in rulebase that influence the behavior of the computer controlled character. However, the weight updating mechanism of DS is not effective if improper initialization of the rulebase is done. In our previous work, we proposed a complementary method to DS that replaces inefficient rules with randomly generated rules. In the present work, we propose three more methods and compare them with the previously proposed one and with the original DS, using a simulator in which one adaptive character duels against one hard-coded character (HC). Our finding is that the method that replaces an inefficient rule with the rule least similar, among the given candidates, to the inefficient one is of the best performance, in terms of the winning rate against HC, for mediocre and weak initial rulebase conditions. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.ice.ci.ritsumei.ac.jp/~ruck/PAP/dime-arts06.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
