AI in Game Theory: Theory and Applications

Dear Colleagues, 

In Game Theory, every agent tries to maximize their own profit (utility, payoff, …), in possible competition (mutual dependence) with each other, and, therefore, optimal decisions occur in the presence of utility tradeoffs.

In comparison to a simple multi-objective optimization problem, in Game Theory, the payoff functions of the players vary, showing an interdependence, a kind of indirect interaction, since the payoff of one player depends also upon the strategies of the other players; any player directly affects the payoffs of the others. Often, when binding agreements are allowed, the complex nature of the interaction does not allow us to find compromised solutions in closed-forms. In this case, solving the problem consists of computing (or approximating) a representative boundary of Pareto optimal solutions.

Evolutionary algorithms, which are evolutionary AI-based computer applications, are popular approaches that generate Pareto optimal solutions to Game Theory problems. They use mechanisms that are typically associated with biological evolution and solve problems by continuously exploring promising search space.

AI can so improve decision-making in Game Theory thanks to the ability of rapidly analyzing big sets of data while simulating many different scenarios of the strategy spaces, and thanks to the ability of remembering what happened in previous games and taking into account the most convenient search space for improving the solution.

In this Special Issue, we encourage submissions providing possible applications of AI in Game Theory. The topics of interest for this publication include, but are not limited to, the following:

• Artificial Intelligence in Game Theory.
• Artificial Intelligence in decision-making.
• Evolutionary algorithms in Game Theory.

Machine learning in Pareto fronts.

Dr. Alessia Donato
Prof. Dr. David Carfì
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• artificial intelligence
• Game Theory
• decision-making
• evolutionary algorithm
• Pareto front
• machine learning