The Replicator Equation as an Inference Dynamic

2009/11/09 by Marc Harper, Harper, Marc · 6 citations
Biochemistry, Genetics and Molecular Biology · Physics and Astronomy · Social Sciences · #37N25 #Dynamical Systems (math.DS) #Evolution and Genetic Dynamics #Evolutionary Game Theory and Cooperation #FOS: Computer and information sciences #FOS: Mathematics #Information Theory (cs.IT) #Opinion Dynamics and Social Influence #Secondary: 62F15

paper · pdf · doi:10.48550/arxiv.0911.1763

openalex publication_date 2009/11/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The replicator equation is interpreted as a continuous inference equation and a formal similarity between the discrete replicator equation and Bayesian inference is described. Further connections between inference and the replicator equation are given including a discussion of information divergences and exponential families as solutions for the replicator dynamic, using Fisher information and information geometry.

Citations

• Information Geometry and Evolutionary Game Theory

Cited by

• The Universe Learning Itself: On the Evolution of Dynamics from the Big Bang to Machine Intelligence
• Thermodynamics + Natural Selection = Bayesian Inference
• Fitness and Overfitness: Implicit Regularization in Evolutionary Dynamics
• The Price equation reveals a universal force-metric-bias law of algorithmic learning and natural selection
• On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning
• Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flows

Related

• Replicator Equation: Applications Revisited
• A probabilistic interpretation of replicator-mutator dynamics
• Replicator equations and the principle of minimal production of information
• Deep learning approach for predicting the replicator equation in evolutionary game theory
• How to explore replicator equations?