A generalized game theoretic framework for mining communities in complex networks

Gao, Guangliang; Cao, Jie; Bu, Zhan; Li, Hui-Jia; Wu, Zhang

doi:10.1016/j.eswa.2017.10.058

Cited by 11 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent decades, an enormous amount of research on developing various types of AI players [1] has been conducted. One recent example of groundbreaking progress is the advent of AlphaGo [2], a fantastic Go player, which has drawn attention from diverse fields, including artificial intelligence (AI) [3], expert systems, consumer behaviors [4], traffic analysis attacks [5], and psychology, due to the extensive application of game theory [5][6][7][8][9][10]. Though it is extremely good at complex data processing and computing and plays a decisive role in the success of research on AI players [11,12], the machine learning technique fails to offer an appropriate way for AI players to make decisions based on rigorous reasoning.…”

Section: Introductionmentioning

confidence: 99%

A Formal Representation for Intelligent Decision-Making in Games

Liu,

Zhang,

Zhang

et al. 2023

Mathematics

View full text Add to dashboard Cite

The study of intelligent game-playing has gained tremendous attention in the past few decades. The recent development of artificial intelligence (AI) players (e.g., the Go player AlphaGo) has made intelligent game-playing even more prominent in both academia and industry. The performance of state-of-the-art AI players benefits greatly from machine learning techniques, based on which, players can make estimations and decisions even without understanding the games. Although AI machines show great superiority over humans in terms of data processing and complex computation, there remains a vast distance between artificial intelligence and human intelligence with respect to the abilities of context understanding and reasoning. In this paper, we explore the theoretical foundation of intelligent game-playing from a logical perspective. The proposed logic, by considering the computational limits in practical game-playing, drops the ideal assumptions in existing logics for the classical game model. We show that under logical framework, the basis of decision-making for agents in game scenarios can be formally represented and analyzed. Moreover, by characterizing the solutions of games, this logic is able to formalize players’ rational decision-making during practical game-playing.

show abstract

Section: Introductionmentioning

confidence: 99%

A Formal Representation for Intelligent Decision-Making in Games

Liu,

Zhang,

Zhang

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…13,14 Compared with QSAR and other calculation methods, the model shows superior performance in calculation speed and accuracy. In recent years, many deep-seated generative models have been proposed, including variational automatic encoder, 15 generative game network 16 and terminal RNN. 17 They understood the basic data distribution in an unsupervised environment and explored the broad space of pharmaceutical chemistry by encoding molecules into a continuous potential space.…”

Section: Introductionmentioning

confidence: 99%