Learning mixed equilibria
From MaRDI portal
Publication:1308819
DOI10.1006/game.1993.1021zbMath0790.90092OpenAlexW2070214254MaRDI QIDQ1308819
Drew Fudenberg, David M. Kreps
Publication date: 23 June 1994
Published in: Games and Economic Behavior (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1006/game.1993.1021
2-person games (91A05) Memory and learning in psychology (91E40) Multistage and repeated games (91A20)
Related Items (only showing first 100 items - show all)
Match length realization and cooperation in indefinitely repeated games ⋮ Belief-based equilibrium ⋮ Information-theoretic bounded rationality and \(\epsilon\)-optimality ⋮ Learning in extensive-form games. I: Self-confirming equilibria ⋮ Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term ⋮ Stochastic approximation to understand simple simulation models ⋮ On Best-Response Dynamics in Potential Games ⋮ Fictitious play in an evolutionary environment ⋮ Learning to learn, pattern recognition, and Nash equilibrium ⋮ Belief affirming in learning processes ⋮ Individual learning in normal form games: Some laboratory results ⋮ Learning and decision costs in experimental constant sum games ⋮ Learning in perturbed asymmetric games ⋮ Learning competitive market balance ⋮ Evolutionary game theory: a renaissance ⋮ Learning from personal experience: One rational gay and the justification of myopia ⋮ On the convergence of beliefs within populations in games with learning ⋮ Multi-rate threshold FlipThem ⋮ Evolution in games with randomly disturbed payoffs ⋮ Large deviations and equilibrium selection in large populations ⋮ Asymptotic pseudotrajectories and chain recurrent flows, with applications ⋮ Perturbations of set-valued dynamical systems, with applications to game theory ⋮ Network games; adaptations to Nash-Cournot equilibrium ⋮ An evolutionary interpretation of mixed-strategy equilibria ⋮ Reputation versus social learning ⋮ On the approximation performance of fictitious play in finite games ⋮ An adaptive learning model with foregone payoff information ⋮ Payoff information and learning in signaling games ⋮ Sampling best response dynamics and deterministic equilibrium selection ⋮ Robustness Properties in Fictitious-Play-Type Algorithms ⋮ Stochastic fictitious play with continuous action sets ⋮ Heterogeneous beliefs and local information in stochastic fictitious play ⋮ Fast convergence in evolutionary models: a Lyapunov approach ⋮ Learning in monotone Bayesian games ⋮ Evolution and equilibrium under inexact information. ⋮ Heterogeneous information lags and evolutionary stability ⋮ Learning Equilibria of a Stochastic Game on Gaussian Interference Channels with Incomplete Information ⋮ Reinforcement learning in population games ⋮ Fictitious play in networks ⋮ Dynamic model of market of patents and equilibria in technology stocks. ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Search for maximum points of a vector criterion based on decomposition properties ⋮ Regular potential games ⋮ Convergent multiple-timescales reinforcement learning algorithms in normal form games ⋮ Probabilistic interpretations of integrability for game dynamics ⋮ Monotone imitation dynamics in large populations ⋮ Convergence in models with bounded expected relative hazard rates ⋮ Selective revelation of public information and self-confirming equilibrium ⋮ Evolution in Bayesian games. II: Stability of purified equilibria ⋮ Learning purified mixed equilibria ⋮ Learning in Games ⋮ Consistency and cautious fictitious play ⋮ Learning in games with strategic complementarities revisited ⋮ Stochastic approximation, cooperative dynamics and supermodular games ⋮ An experiment to evaluate Bayesian learning of Nash equilibrium play ⋮ Learning in games using the imprecise Dirichlet model ⋮ Choosing the equilibrium behavior in an infinitely repeated \(2 \times 2\) game for conservative and innovative gamers ⋮ Trembling hand perfection for mixed quantal/best response equilibria ⋮ Identification and testing of modes in beliefs ⋮ Mixed equilibria are unstable in games of strategic complements ⋮ Learning in games with unstable equilibria ⋮ Player-compatible learning and player-compatible equilibrium ⋮ Generalised weakened fictitious play ⋮ REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES ⋮ Merging and testing opinions ⋮ LEARNING, EVOLUTION AND POPULATION DYNAMICS ⋮ The Nash equilibrium: A perspective ⋮ Asymptotic behavior of Bayesian learners with misspecified models ⋮ Games with coupled populations: an experiment in continuous time ⋮ Convergence results on stochastic adaptive learning ⋮ Naive adaptive behavior and the observability of gambles ⋮ Deterministic approximation of best-response dynamics for the matching pennies game ⋮ Evolution with changing mutation rates ⋮ A learning approach to auctions ⋮ Nonparametric adaptive learning with feedback ⋮ Mixed equilibria and dynamical systems arising from fictitious play in perturbed games ⋮ Conditional universal consistency. ⋮ A note on best response dynamics. ⋮ On the nonconvergence of fictitious play in coordination games ⋮ If multi-agent learning is the answer, what is the question? ⋮ An economist's perspective on multi-agent learning ⋮ Learning, matching, and aggregation ⋮ A payoff uncertainty explanation of results in experimental centipede games ⋮ Fictitious play in \(2\times 3\) games ⋮ Experimentation, imitation, and stochastic stability ⋮ On attitude polarization under Bayesian learning with non-additive beliefs ⋮ Adaptive learning and iterated weak dominance ⋮ Towards a taxonomy of learning dynamics in \(2\times 2\) games ⋮ Convergence conditions for the Brown-Robinson iterative method for bimatrix games ⋮ Economists' models of learning ⋮ SOLVING LARGE GAMES WITH SIMULATED FICTITIOUS PLAY ⋮ Time to absorption in discounted reinforcement models. ⋮ Reciprocity and cooperation in repeated coordination games: The principled-player approach ⋮ Strategic similarity and emergent conventions: evidence from similar stag hunt games ⋮ Unnamed Item ⋮ Introducing disappointment dynamics and comparing behaviors in evolutionary games: some simulation results ⋮ ADVANCES IN DISTRIBUTED OPTIMIZATION USING PROBABILITY COLLECTIVES ⋮ On (un)knots and dynamics in games ⋮ Predicting human cooperation in the prisoner's dilemma using case-based decision theory ⋮ Entropic penalties in finite games
This page was built for publication: Learning mixed equilibria
