Why imitate, and if so, how? A boundedly rational approach to multi-armed bandits

DOI10.1006/jeth.1997.2347zbMath0895.90003OpenAlexW1551911640MaRDI QIDQ1381965

Publication date: 1 April 1998

Published in: Journal of Economic Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jeth.1997.2347

zbMATH Keywords

imitation learning rules optimal behaviour

Mathematics Subject Classification ID

Decision theory (91B06) Economic growth models (91B62) Population dynamics (general) (92D25) Stochastic games, stochastic differential games (91A15) Memory and learning in psychology (91E40)

Related Items

On the level of cooperative behavior in a local-interaction model. ⋮ Imitation dynamics with payoff shocks ⋮ Cyclical behavior of evolutionary dynamics in coordination games with changing payoffs ⋮ Decentralized pricing and the equivalence between Nash and Walrasian equilibrium ⋮ Riemannian game dynamics ⋮ Social learning and the shadow of the past ⋮ The evolution of social learning rules: payoff-biased and frequency-dependent biased transmission ⋮ Evolutionary games in deme structured, finite populations ⋮ Success-biased social learning: cultural and evolutionary dynamics ⋮ A finite population destroys a traveling wave in spatial replicator dynamics ⋮ Cooperation can emerge in prisoner's dilemma from a multi-species predator prey replicator dynamic ⋮ A note on adjusted replicator dynamics in iterated games ⋮ Ordinal imitative dynamics ⋮ Adverse selection, heterogeneous beliefs, and evolutionary learning ⋮ On the evolution of compliance and regulation with tax evading agents ⋮ Evolution and jump in a Walrasian framework ⋮ The effects of nonlinear imitation probability on the evolution of cooperation ⋮ Evolutionary game theory: a renaissance ⋮ Game theory and the evolution of cooperation ⋮ Imitation processes with small mutations ⋮ Chaos in collective health: fractal dynamics of social learning ⋮ Experiments on individual strategy updating in iterated snowdrift game under random rematching ⋮ Success-biased social learning in a one-consumer, two-resource model ⋮ Evolutionary stability in first price auctions ⋮ The evolution of cooperation through imitation ⋮ Learning through reinforcement and replicator dynamics ⋮ Evolutionary network games: equilibria from imitation and best response dynamics ⋮ The multi-armed bandit, with constraints ⋮ Replicator based on imitation for finite and arbitrary networked communities ⋮ Learning by similarity-weighted imitation in winner-takes-all games ⋮ Unbeatable imitation ⋮ Corruption driven by imitative behavior ⋮ Simulated trust: a cheap social learning strategy ⋮ Errors can increase cooperation in finite populations ⋮ Dynamic choice in a complex world ⋮ A class of evolutionary models for participation games with negative feedback ⋮ Evolution and equilibrium under inexact information. ⋮ Experimental oligopolies modeling: a dynamic approach based on heterogeneous behaviors ⋮ Effects of update rules on networked \(N\)-player trust game dynamics ⋮ Word-of-mouth learning. ⋮ Imitation and the evolution of Walrasian behavior: theoretically fragile but behaviorally robust ⋮ Why learning doesn't add up: Equilibrium selection with a composition of learning rules ⋮ Technology choice in an evolutionary oligopoly game ⋮ On the convergence of genetic learning in a double auction market ⋮ Learning by imitation ⋮ Separating the hawks from the doves: evidence from continuous time laboratory games ⋮ Long-run selection and the work ethic ⋮ Market selection with an endogenous state ⋮ Convergence in models with bounded expected relative hazard rates ⋮ Evolutionary imitative dynamics with population-varying aspiration levels ⋮ Cournot competition, imitation, and information networks ⋮ The evolution of fairness under an assortative matching rule in the ultimatum game ⋮ The Walrasian output beats the market ⋮ An example of dynamic (in)consistency in symmetric extensive form evolutionary games ⋮ Imitation with asymmetric memory ⋮ A finite population ESS and a long run equilibrium in an \(n\) players coordination game ⋮ Learning in society ⋮ Imitation and the role of information in overcoming coordination failures ⋮ On learning dynamics underlying the evolution of learning rules ⋮ Evolutionary competition between adjustment processes in Cournot oligopoly: instability and complex dynamics ⋮ Evolutionary potential games on lattices ⋮ Network structure, games, and agent dynamics ⋮ Positive welfare effects of trade barriers in a dynamic partial equilibrium model ⋮ Empty nodes affect conditional cooperation under reinforcement learning ⋮ Asymmetric micro-dynamics in spatial anonymous public goods game ⋮ An oligopoly model with rational and imitation rules ⋮ From imitation to collusion: long-run learning in a low-information environment ⋮ Imitation and experimentation in changing contests ⋮ Effects of asynchronism on evolutionary games ⋮ The spatial ultimatum game revisited ⋮ Stochastic imitation in finite games ⋮ The asset market game ⋮ Subgames within large games and the heuristic of imitation ⋮ Evolutionary game dynamics in populations with different learners ⋮ An introduction to \textit{ABED}: agent-based simulation of evolutionary game dynamics ⋮ Imitation in heterogeneous populations ⋮ Neutral stability, drift, and the diversification of languages ⋮ Stability for best experienced payoff dynamics ⋮ Choosing a good toolkit. I: Prior-free heuristics ⋮ Brown-von Neumann-Nash dynamics: The continuous strategy case ⋮ Imitation and luck: An experimental study on social sampling ⋮ Fixation times in deme structured, finite populations with rare migration ⋮ Learning and market clearing: theory and experiments ⋮ Evolutionary game dynamics and the analysis of agent-based imitation models: the long run, the medium run and the importance of global analysis ⋮ A note on best response dynamics. ⋮ Cultural and evolutionary dynamics with best-of-\(k\) learning when payoffs are uncertain ⋮ The dynamic (in)stability of backwards induction ⋮ Local stability of smooth selection dynamics for normal form games ⋮ Monotone imitation ⋮ Chaos in the cobweb model with a new learning dynamic ⋮ Continuous approximations of stochastic evolutionary game dynamics ⋮ Which one should I imitate? ⋮ An oligopoly model with best response and imitation rules ⋮ Stochastically stable states in an oligopoly with differentiated goods: Equivalence of price and quantity strategies ⋮ Subgame monotonicity in extensive form evolutionary games ⋮ Pairwise comparison dynamics and evolutionary foundations for Nash equilibrium ⋮ Tributes to Bill Sandholm ⋮ An evolutionary analysis of insurance markets with adverse selection. ⋮ Endogenous fluctuations under evolutionary pressure in Cournot competition ⋮ On the role of the group composition for achieving optimality ⋮ EVOLUTIONARY AND DYNAMIC STABILITY IN SYMMETRIC EVOLUTIONARY GAMES WITH TWO INDEPENDENT DECISIONS ⋮ DOES NOISE UNDERMINE THE FIRST-MOVER ADVANTAGE? AN EVOLUTIONARY ANALYSIS OF BAGWELL'S EXAMPLE ⋮ On the evolutionary selection of sets of Nash equilibria ⋮ Analysis of Economic Behaviour in Evolutionary Model of Tax Control Under Information Diffusion ⋮ Behavioral refuges and predator-prey coexistence ⋮ Poverty Traps, Rationality and Evolution ⋮ ON THE SURVIVAL OF COOPERATION UNDER DIFFERENT MATCHING SCHEMES ⋮ Cooperation, imitation and partial rematching ⋮ Imitation, coordination and the emergence of Nash equilibrium ⋮ Dissonance Minimization as a Microfoundation of Social Influence in Models of Opinion Formation ⋮ Interior Convergence Under Payoff Monotone Selections and Proper Equilibrium: Application to Equilibrium Selection ⋮ Imitation dynamics with time delay ⋮ The emergence and implementation of pool exclusion in spatial public goods game with heterogeneous ability-to-pay ⋮ Imitative and best response behaviors in a nonlinear Cournotian setting ⋮ Social learning strategies and cooperative behaviour: evidence of payoff bias, but not prestige or conformity, in a social dilemma game ⋮ Evolution of social learning with payoff and content bias ⋮ A financial market model with endogenous fundamental values through imitative behavior ⋮ Evolutionary robustness of dominant strategy implementation ⋮ Which misspecifications persist? ⋮ Similarity Suppresses Cyclicity: Why Similar Competitors Form Hierarchies ⋮ The logit dynamic in supermodular games with a continuum of strategies: a deterministic approximation approach ⋮ Social learning between groups: imitation and the role of experience ⋮ Evolutionary dynamics in heterogeneous populations: a general framework for an arbitrary type distribution ⋮ Dynamically stable sets in infinite strategy spaces ⋮ Characterizing oscillations in heterogeneous populations of coordinators and anticoordinators ⋮ Stochastic replicator dynamics: a theoretical analysis and an experimental assessment ⋮ Co-evolution of strategies and update rules in the prisoner's dilemma game on complex networks ⋮ Imitation-theory and experimental evidence ⋮ Evolutionary Game Theory ⋮ Travelling waves for games in economics and biology ⋮ Experimentally observed imitation and cooperation in price competition on the circle ⋮ Cultural coevolution of norm adoption and enforcement when punishers are rewarded or non-punishers are punished ⋮ Cycles of aggregate behavior in theory and experiment. ⋮ The propagation of chaos for interacting individuals in a large population ⋮ Correlated equilibrium in evolutionary models with subpopulations ⋮ Evolutionary game dynamics ⋮ Exploration dynamics in evolutionary games ⋮ Equilibrium Selection in the Two-Population KMR Model ⋮ Imitation Dynamic and Nash Equilibrium in Cournot Oligopoly with Capacities ⋮ The projection dynamic and the geometry of population games ⋮ The projection dynamic and the replicator dynamic ⋮ The cultural Red King effect ⋮ A GENERALIZED MODEL OF BEST RESPONSE ADAPTATION ⋮ Sample Path Large Deviations for Stochastic Evolutionary Game Dynamics ⋮ EFFECTS OF SPACE IN 2 × 2 GAMES ⋮ Optimal guessing: choice in complex environments ⋮ Stability of the replicator equation with continuous strategy space ⋮ Excess payoff dynamics and other well-behaved evolutionary dynamics ⋮ Introducing disappointment dynamics and comparing behaviors in evolutionary games: some simulation results ⋮ Equilibrium selection via replicator dynamics in \(2 \times 2\) coordination games ⋮ The dynamics of costly signaling ⋮ Stationary distributions of noisy replicator dynamics in the Ultimatum game

Cites Work