Convergence in models with bounded expected relative hazard rates
From MaRDI portal
(Redirected from Publication:472194)
Abstract: We provide a general framework to study stochastic sequences related to individual learning in economics, learning automata in computer sciences, social learning in marketing, and other applications. More precisely, we study the asymptotic properties of a class of stochastic sequences that take values in and satisfy a property called "bounded expected relative hazard rates." Sequences that satisfy this property and feature "small step-size" or "shrinking step-size" converge to 1 with high probability or almost surely, respectively. These convergence results yield conditions for the learning models in B"orgers, Morales, and Sarin (2004), Erev and Roth (1998), and Schlag (1998) to choose expected payoff maximizing actions with probability one in the long run.
Recommendations
- Economic Dynamics with Learning: New Stability Results
- Convergence results on stochastic adaptive learning
- Convergence in models of misspecified learning
- Strong convergence of least squares learning to rational expectations
- Convergence of least squares learning in self-referential discontinuous stochastic models.
Cites work
- A new product growth for model consumer durables
- A Note on the Linear Reinforcement Scheme for Variable-Structure Stochastic Automata
- A penalized bandit algorithm
- A sequential design for maximizing the probability of a favourable response
- A Stochastic Approximation Method
- Attainability of boundary points under reinforcement learning
- Bounds on the Convergence Probabilities of Learning Automata
- Convergence in models with bounded expected relative hazard rates
- Evolutionary dynamics of cooperation
- Expedient and Monotone Learning Rules
- How Fast Is the Bandit?
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 1405930 (Why is no real title available?)
- Learning and risk aversion
- Learning Automata - A Survey
- Learning from Neighbours
- Learning mixed equilibria
- Monotone imitation
- On ergodic two-armed bandits
- On the convergence of reinforcement learning
- On the linear model with two absorbing barriers
- Randomized urn models revisited using stochastic approximation
- Selection dynamics and adaptive behavior without much information
- Stochastic approximation methods for constrained and unconstrained systems
- Stochastic approximation, cooperative dynamics and supermodular games
- Stochastic Estimation of the Maximum of a Regression Function
- Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria
- When can the two-armed bandit algorithm be trusted?
- Why imitate, and if so, how? A boundedly rational approach to multi-armed bandits
- Word-of-Mouth Communication and Social Learning
Cited in
(6)- Bounds for the hazard gradients in the competing risks set up
- Social learning and the shadow of the past
- Evolutionary game theory: a renaissance
- On the robustness of learning in games with stochastically perturbed payoff observations
- Convergence in models with bounded expected relative hazard rates
- On a class of aggregation operators and learning in expert systems
This page was built for publication: Convergence in models with bounded expected relative hazard rates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q472194)
