Stochastic evolution in populations of ideas
arXiv:1609.04443 · doi:10.1038/srep40580
Abstract
It is known that learning of players who interact in a repeated game can be interpreted as an evolutionary process in a population of ideas. These analogies have so far mostly been established in deterministic models, and memory loss in learning has been seen to act similarly to mutation in evolution. We here propose a representation of reinforcement learning as a stochastic process in finite "populations of ideas". The resulting birth-death dynamics has absorbing states and allows for the extinction or fixation of ideas, marking a key difference to mutation-selection processes in finite populations. We characterize the outcome of evolution in populations of ideas for several classes of symmetric and asymmetric games.
arXiv comment37 pages, 20 figures
References in corpus (13)
- Evolutionary game theory: Temporal and spatial effects beyond replicator dynamics
- Coevolutionary Dynamics: From Finite to Infinite Populations
- Fixation of strategies for an evolutionary game in finite populations
- Stochastic Models of Evolution in Genetics, Ecology and Linguistics
- Time Scales in Evolutionary Dynamics
- Oscillatory Dynamics in Rock-Paper-Scissors Games with Mutations
- Coupled Replicator Equations for the Dynamics of Learning in Multiagent Systems
- Generalisation of the Eyring-Kramers transition rate formula to irreversible diffusion processes
- Fixation times in evolutionary games under weak selection
- Stability and Diversity in Collective Adaptation
- Evolutionary dynamics, intrinsic noise and cycles of co-operation
- Intrinsic noise in game dynamical learning
- Fixation and escape times in stochastic game learning