Improving behavior of computer game bots using fictitious play

Patel, Ushma Kesha; Patel, Purvag; Hexmoor, Henry; Carver, Norman

doi:10.1007/s11633-012-0625-5

Cited by 6 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Banyak penelitian yang telah membuktikan perilaku agen dengan FMS mudah diprediksi [20]- [22]. Agen cerdas yang disebut dengan "bot" dilatih dalam beberapa simulasi permainan yang bersifiat fiktif (fictitious play).…”

Section: Agen Cerdasunclassified

Probabilitas dalam Finite State Machine Agen Cerdas Edugame “Ajut-Ajut Kids”

Lailiyah

Yunita

Mallala

et al. 2019

Jurnal Nasional Teknik Elektro dan Teknologi Informasi

View full text Add to dashboard Cite

Educational game "Ajut-ajut Kids" is developed in multimedia stages to introduce the Dayak Benuaq language for children. In this matching game, players must match two or more images and words in Dayak language. This study applies randomization to shuffle position of images and words in each round. It makes the game more challenging. Random and probability in-game agents are also applied, which will accompany children to play the kid character in Dayak clothes. Game agents, which apply the Finite State Machine (FSM) model, will provide expressions like pleasure, sadness, etc., according to the child's playing style. Random implementation and credibility in the FSM model allows agents to give random expressions. This makes the agent more natural. The result of this study proves randomization and probability have succeeded make this game more interesting and interactive to children. Intisari-Edugame "Ajut-ajut Kids" dibangun melalui tahapan multimedia untuk mengenalkan pembelajaran bahasa Dayak Benuaq kepada anak. Permainan ini berjenis matching, yaitu pemain harus mencocokkan gambar dan kata bahasa Dayak. Makalah ini menerapkan teknik pengacakan pada susunan gambar dan kata pada setiap babak untuk membuat permainan tidak berkurang tantangannya. Pengacakan dan probabilitas juga diterapkan dalam agen cerdas yang menemani anak bermain dalam bentuk karakter cilik berbaju adat Dayak. Agen cerdas, yang menerapkan model Finite State Machine (FSM), akan memberikan ekspresi senang, sedih, dan sebagainya, sesuai gaya bermain anak. Adanya pengacakan dan probabilitas dalam model FSM membuat agen kadang-kadang juga dapat memberikan ekspresi yang acak. Hal ini membuat agen lebih natural. Hasil pengujian membuktikan pengacakan dan probabilitas berhasil membuat permainan ini tidak monoton dan lebih interaktif.

show abstract

Section: Agen Cerdasunclassified

Probabilitas dalam Finite State Machine Agen Cerdas Edugame “Ajut-Ajut Kids”

Lailiyah

Yunita

Mallala

et al. 2019

Jurnal Nasional Teknik Elektro dan Teknologi Informasi

View full text Add to dashboard Cite

show abstract

“…For example, it is critical if a Blackboard architecture is used in the development of new solutions for path planning for unmanned aerial [4] , ground [5,6] and underwater vehicles [7] . Autonomous control of game agents [8] would also drive a need for timely decision making. The evaluation conducted herein, thus, supports assessment of the suitability of pruning best path and naïve solvers for these applications.…”

Section: Introductionmentioning

confidence: 99%

Comparing the effect of pruning on a best path and a naïve-approach blackboard solver

Straub

2015

Int. J. Autom. Comput.

View full text Add to dashboard Cite

A naïve solver is one approach that can be used to identify prospective solutions based on data on (or projected to be on) a Blackboard Architecture s blackboard. The naïve solver approach doesn t implement heuristics or other techniques to determine what solution paths to attempt first. Instead, it runs the blackboard forward (simulating what would occur if data were gradually added to the blackboard at a faster-than-real time rate). The approach doesn t guarantee that an optimal solution will be found and will need to be run repetitively to create multiple solutions for comparison. This paper assesses the effect of pre-pruning the blackboard s facts and rules to remove those that are not relevant (e.g., facts that cannot be asserted, rules that cannot be triggered) or which produce irrelevant facts and pruning actions that produce irrelevant facts (and/or trigger other similarly useless actions). It describes the Blackboard implementation and its utility, explains the pruning process used and presents quantitative and qualitative assessment of the utility of pruning to a naïve solver s operations. This value is extrapolated to facilitate consideration of a more robust pruning process which also removes low-value facts, actions and rules in addition to those being removed due to their uselessness.

show abstract