Learning and Evolution in Games
A section of Games (ISSN 2073-4336).
Section Information
Learning and evolution in games cover a wide range of applications of game theory in biology, computer science, control theory, economics, and other social sciences. The common motivation is to understand the dynamics and resulting convergence properties of interactions in dynamic populations and multi-agent systems.
The Learning and Evolution in Games Section of Games publishes contributions in any of these areas. We also encourage contributions that elicit methodological and conceptual connections between different applications, and contributions that showcase new applications. We invite all kinds of papers, theoretical, computational, experimental and empirical, and are also interested in review articles.
Keywords
- Bayesian learning
- Behavioral game theory
- Belief-based learning
- Best-response dynamics
- Conditional cooperation
- Cultural evolution
- Decentralized control
- Dynamic matching
- Dynamic systems
- Evolutionary game theory
- Emergence of conventions
- Equilibrium selection
- Evolution of cooperation
- Evolution of social norms
- Group selection
- Imitation
- Kin selection
- Learning algorithms
- Machine learning
- Misspecified learning
- Preference evolution
- Reciprocity
- Reinforcement learning
- Etc.
Editorial Board
Special Issues
Following special issues within this section are currently open for submissions:
- In Pursuit of the Unification of Evolutionary Dynamics (Deadline: 30 September 2023)
- Evolution of Cooperation and Evolutionary Game Theory (Deadline: 31 December 2023)
- Learning and Evolution in Games, 1st Edition (Deadline: 31 January 2024)
