.png){kind=icon}
返回
AutoGT: Automatic Generation of Game Trees for Algorithm Benchmarking
.png){kind=icon}
PRE
AI
DOI：10.1109/TG.2025.3566891.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Game tree search algorithms play a vital role in application of computational and artificial intelligence methods in games and sequential combinatorial optimization problems. This article addresses the need for robust and comprehensive benchmarking of these algorithms through the procedural generation of benchmarks. We introduce a novel Automatic Game Tree automatic game tree (AutoGT) generator built upon the idea of top-down propagation of various game parameters. Thanks to its extensive parameterization, AutoGT enables researchers to evaluate their methods on virtually unlimited number of unique benchmarks. To demonstrate the efficacy and usefulness of the generator, we present comparative results of several standard game-playing algorithms: a game theory optimal player, a player making moves according to a uniform random distribution, and a few variants of Monte Carlo Tree Search-based players. Our findings indicate that for a given set of benchmark parameters, the results are repeatable with low deviation. However, when testing across various parameter settings, the performance becomes more diverse, allowing for a broader and more detailed assessment of the algorithms. This article includes a link to the full code of AutoGT benchmark generation method.
Keyword:
Games
Benchmark testing
Generators
Planning
Video games
Taxonomy
Monte Carlo methods
Evolutionary computation
Training
Surveys
Game theory
game tree search
Monte Carlo tree search (MCTS)
procedural generation
期刊
I
IF:
2.8
论文数:
45
被引数:
0
机构
引用论文
The 2023 International Planning CompetitionTaitler, A.; Alford, R.; Espasa, J.; Behnke, G.; Fiser, D.; Gimelfarb, M.; Pommerening, F.; Sanner, S.; Scala, E.; Schreiber, D.; 等. 2023年国际规划竞赛. 人工智能杂志. 2024, 45, 280–296. [Google Scholar] [CrossRef].png)
AI Magazine
AI MagazineIF0
PREAI
分享收藏
分享收藏分享收藏
查看更多内容