Convergence in models with bounded expected relative hazard rates
From MaRDI portal
Publication:472194
DOI10.1016/j.jet.2014.09.014zbMath1330.91040arXiv1208.3088OpenAlexW2115848770MaRDI QIDQ472194
Publication date: 19 November 2014
Published in: Journal of Economic Theory (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1208.3088
convergencestochastic approximationsocial learninghazard ratedynamic systemindividual learningsubmartingaletwo-armed bandit algorithm
Learning and adaptive systems in artificial intelligence (68T05) Stopping times; optimal stopping problems; gambling theory (60G40) Memory and learning in psychology (91E40) Rationality and learning in game theory (91A26)
Related Items
On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Social learning and the shadow of the past ⋮ Evolutionary game theory: a renaissance ⋮ Convergence in models with bounded expected relative hazard rates
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Randomized urn models revisited using stochastic approximation
- On ergodic two-armed bandits
- Convergence in models with bounded expected relative hazard rates
- Stochastic approximation, cooperative dynamics and supermodular games
- Monotone imitation
- A penalized bandit algorithm
- Stochastic approximation methods for constrained and unconstrained systems
- Learning mixed equilibria
- Why imitate, and if so, how? A boundedly rational approach to multi-armed bandits
- On the convergence of reinforcement learning
- When can the two-armed bandit algorithm be trusted?
- Learning and risk aversion
- On the linear model with two absorbing barriers
- Attainability of boundary points under reinforcement learning
- Selection dynamics and adaptive behavior without much information
- A New Product Growth for Model Consumer Durables
- How Fast Is the Bandit?
- Bounds on the Convergence Probabilities of Learning Automata
- Learning from Neighbours
- A sequential design for maximizing the probability of a favourable response
- Learning Automata - A Survey
- Word-of-Mouth Communication and Social Learning
- Expedient and Monotone Learning Rules
- Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria
- A Note on the Linear Reinforcement Scheme for Variable-Structure Stochastic Automata
- Stochastic Estimation of the Maximum of a Regression Function
- A Stochastic Approximation Method