Fixation and escape times in stochastic game learning

Abstract

Evolutionary dynamics in finite populations is known to fixate eventually in the absence of mutation. We here show that a similar phenomenon can be found in stochastic game dynamical batch learning, and investigate fixation in learning processes in a simple 2x2 game, for two-player games with cyclic interaction, and in the context of the best-shot network game. The analogues of finite populations in evolution are here finite batches of observations between strategy updates. We study when and how such fixation can occur, and present results on the average time-to-fixation from numerical simulations. Simple cases are also amenable to analytical approaches and we provide estimates of the behaviour of so-called escape times as a function of the batch size. The differences and similarities with escape and fixation in evolutionary dynamics are discussed.

19 pages, 9 figures

References in corpus (10)

• Mobility promotes and jeopardizes biodiversity in rock-paper-scissors games
• Fixation of strategies for an evolutionary game in finite populations
• Coexistence versus extinction in the stochastic cyclic Lotka-Volterra model
• Oscillatory Dynamics in Rock-Paper-Scissors Games with Mutations
• Fixation times in evolutionary games under weak selection
• Spatial Rock-Paper-Scissors Models with Inhomogeneous Reaction Rates
• How limit cycles and quasi-cycles are related in systems with intrinsic noise
• Evolutionary dynamics, intrinsic noise and cycles of co-operation
• The edge of neutral evolution in social dilemmas
• Learning to play public good games

Cited by in corpus (6)

• Cyclic dominance in evolutionary games: A review
• Deterministic limit of temporal difference reinforcement learning for stochastic games
• Balancing selfishness and norm conformity can explain human behavior in large-scale Prisoner's Dilemma games and can poise human groups near criticality
• Nonmonotonic Effects of Migration in Subdivided Populations
• Stochastic evolution in populations of ideas
• Coordination problems on networks revisited: statics and dynamics