Learning, Hypothesis Testing, and Nash Equilibrium. by Foster, D, Young, H

Regret Testing: Learning to Play Nash Equilibrium without Knowing You Have an Opponent. by Foster, D, Young, H

“…We demonstrate a family of simple, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any finite two-person game.…”

Fast Convergence in Population Games by Arieli, I, Young, H

“…A stochastic learning dynamic exchibits fast convergence in a population game if the expected waiting time until the process comes near a Nash equilibrium is bounded above for all sufficiently large populations. …”

Learning by trial and error. by Young, H

“…This rule, called interactive trial and error learning, implements Nash equilibrium behavior in any game with generic payoffs and at least one pure Nash equilibrium.…”

Learning efficient Nash equilibria in distributed systems by Young, H, Pradelski, B

“…We propose a variant of log linear learning that is completely uncoupled and that selects an efficient pure Nash equilibrium in all generic n-person games that possess at least one pure Nash equilibrium. …”

Learning to Play Nash. by Foster, D, Young, H

“…Although there exist rules that converge to Nash equilibrium for special classes of games (like fictuous play in zero-sum games), it is an open question whether players can learn to play Nash in general games without assuming that they have a prior knowledge of their opponent's strategies. …”

Learning by trial and error. by Young, H

“…This paper introduces a simple version of this idea, called interactive trial and error learning, which has the property that it implements Nash equilibrium behavior in any game with generic payoffs and at least one pure Nash equilibrium. …”

Stochastic learning dynamics and speed of convergence in population games by Young, H, Arieli, I

“…We study how long it takes for large populations of interacting agents to come close to Nash equilibrium when they adapt their behavior using a stochastic better reply dynamic. …”

Stochastic learning dynamics and speed of convergence in population games by Arieli, I, Young, H

“…We study how long it takes for large populations of interacting agents to come close to Nash equilibrium when they adapt their behavior using a stochastic better reply dynamic. …”

Learning by trial and error by Young, H

“…This paper introduces a simple version of this idea, called interactive trial and error learning, which has the property that it implements Nash equilibrium behavior in any game with generic payoffs and at least one pure Nash equilibrium. …”

Adaptive learning in systems of interacting agents. by Young, H

“…These rules have the property that, in large classes of games, agents' individual behavior results in Nash equilibrium behavior by the group a high proportion of the time. …”

Payoff-based dynamics for multiplayer weakly acyclic games. by Marden, J, Young, H, Arslan, G, Shamma, J

“…We introduce three different payoff-based processes for increasingly general scenarios and prove that, after a sufficiently large number of stages, player actions constitute a Nash equilibrium at any stage with arbitrarily high probability. …”

The Possible and the Impossible in Multi-Agent Learning. by Young, H

“…The paper surveys recent work on learning in games and delineates the boundary between forms of learning that lead to Nash equilibrium and forms that lead to weaker notions of equilibrium (or none at all).…”

The possible and the impossible in multi-agent learning by Young, H

“…The paper surveys recent work on learning in games and delineates the boundary between forms of learning that lead to Nash equilibrium and forms that lead to weaker notions of equilibrium (or none at all).…”

On the Limits to Rational Learning. by Young, H

“…That is, under any learning rule--including Bayesian updating of common priors--the players' strategies fail to come close to Nash equilibrium with probability one. Furthermore at least one of them is unable to predict the behavior of the other in an asymptotic sense. …”

Learning in a black box: trial-and-error in voluntary contributions games by Young, H, Nax, H, Burton-Chellew, M, Westor, S

“…These features are clearly present when players have no information about the game; but also when players have full informaiton. Convergence to Nash equilibrium occurs at about the same rate in both situations.…”

Learning Dynamics in Games with Stochastic Perturbations. by Kaniovski, Y, Young, H

“…It is shown, using results from stochastic approximation theory, that for 2 x 2 games it converges almost surely to a point that lies close to a stable Nash equilibrium, whether pure or mixed. This generalizes a result of Fudenberg and Kreps, who demonstrate convergence when the game has a unique mixed equilibrium. …”

Learning in a black box by Nax, H, Burton-Chellew, M, West, S, Young, H

“…Theory shows that even when players have no such information, there are simple payoff-based learning rules that lead to Nash equilibrium in many types of games. A key feature of these rules is that subjects search differently depending on whether their payoffs increase, stay constant or decrease. …”

Learning in a black box by Nax, H, Burton-Chellew, M, West, S, Young, H

“…Theory shows that even when players have no such information, there are simple payoff-based learning rules that lead to Nash equilibrium in many types of games. A key feature of these rules is that subjects search differently depending on whether their payoffs increase, stay constant or decrease. …”

Cost Allocation, Demand Revelation, and Core Implementation. by Young, H

“…We propose a simple demand revelation mechanism in which potential customers bid to be served and the regulator accepts a set of bids that maximizes revenues net of costs. In a strong Nash equilibrium, the mechanism reveals the efficient set of customers to serve and covers the costs of serving them, possibly with a surplus for the producer. …”