File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICNC.2010.5583801
- Scopus: eid_2-s2.0-78149316888
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Automatic game AI design by the use of UCT for Dead-End
Title | Automatic game AI design by the use of UCT for Dead-End |
---|---|
Authors | |
Keywords | Automatic AI design CI Dead-End UCT |
Issue Date | 2010 |
Citation | Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010, 2010, v. 7, p. 3846-3850 How to Cite? |
Abstract | Video game AI aims at generating an intelligent game opponent which is to compete with player, so game AI design plays an important role in the development of game. Nowadays, most of the game AI is implemented by FSM. But this mechanism has some drawbacks, so we need a mechanism to design game AI automatically instead of FSM. The process of automatic game AI design by UCT is introduced in this paper. In this process, we only take the meta-rules into consideration, while those many complicated detail knowledge is acquired by simulation. Here we propose the approach of UCT-controlled NPC based on CI (computational intelligence). However, this approach will consume lots of computational resources, and the acquired knowledge cannot be stored. To solve this problem, we train Artificial Neural Network (ANN) to make it reusable. The whole design process is validated on the Test-Bed of the game Dead-End. We conclude that from both the simplification of implementation and the reusability, this process outperforms FSM. ©2010 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/348930 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shi, Zhiyuan | - |
dc.contributor.author | Wang, Yamin | - |
dc.contributor.author | He, Suoju | - |
dc.contributor.author | Wang, Junping | - |
dc.contributor.author | Dong, Jie | - |
dc.contributor.author | Liu, Yuanwei | - |
dc.contributor.author | Jiang, Teng | - |
dc.date.accessioned | 2024-10-17T06:55:00Z | - |
dc.date.available | 2024-10-17T06:55:00Z | - |
dc.date.issued | 2010 | - |
dc.identifier.citation | Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010, 2010, v. 7, p. 3846-3850 | - |
dc.identifier.uri | http://hdl.handle.net/10722/348930 | - |
dc.description.abstract | Video game AI aims at generating an intelligent game opponent which is to compete with player, so game AI design plays an important role in the development of game. Nowadays, most of the game AI is implemented by FSM. But this mechanism has some drawbacks, so we need a mechanism to design game AI automatically instead of FSM. The process of automatic game AI design by UCT is introduced in this paper. In this process, we only take the meta-rules into consideration, while those many complicated detail knowledge is acquired by simulation. Here we propose the approach of UCT-controlled NPC based on CI (computational intelligence). However, this approach will consume lots of computational resources, and the acquired knowledge cannot be stored. To solve this problem, we train Artificial Neural Network (ANN) to make it reusable. The whole design process is validated on the Test-Bed of the game Dead-End. We conclude that from both the simplification of implementation and the reusability, this process outperforms FSM. ©2010 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - 2010 6th International Conference on Natural Computation, ICNC 2010 | - |
dc.subject | Automatic AI design | - |
dc.subject | CI | - |
dc.subject | Dead-End | - |
dc.subject | UCT | - |
dc.title | Automatic game AI design by the use of UCT for Dead-End | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICNC.2010.5583801 | - |
dc.identifier.scopus | eid_2-s2.0-78149316888 | - |
dc.identifier.volume | 7 | - |
dc.identifier.spage | 3846 | - |
dc.identifier.epage | 3850 | - |