equilibrium under fictitious play like learning processes. We use two 4 x 4 games each with a unique mixed Nash equilibrium; one … is stable and one is unstable under learning. Both games are versions of Rock-Paper-Scissors with the addition of a …We report experiments designed to test between Nash equilibria that are stable and unstable under learning. The “TASP …

equilibrium under fictitious play like learning processes. We use two 4 x 4 games each with a unique mixed Nash equilibrium; one … is stable and one is unstable under learning. Both games are versions of Rock-Paper-Scissors with the addition of a …We report experiments designed to test between Nash equilibria that are stable and unstable under learning. The 'TASP …

We investigate the stability of mixed strategy equilibria in 2 person (bimatrix) games under perturbed best response … set of perturbed equilibria is shown also for (rescaled) partnership games (also know as games of identical interest …). Some applications of these result to stochastic learning models are given. …

equilibrium under fictitious play like learning processes. We use two 4 x 4 games each with a unique mixed Nash equilibrium; one … is stable and one is unstable under learning. Both games are versions of Rock-Paper-Scissors with the addition of a …We report experiments designed to test between Nash equilibria that are stable and unstable under learning. The “TASP …

We report experiments designed to test between Nash equilibria that are stable and unstable under learning. The “TASP … equilibrium under a wide class of learning processes. We study two versions of Rock-Paper-Scissors with the addition of a fourth … strategy, Dumb. The unique Nash equilibrium places a weight of 1/2 on Dumb in both games, but in one game the NE is stable …

We investigate games whose Nash equilibria are mixed and are unstable under fictitious play-like learning processes. We … experience that the time average of play often converges in these “unstable” games, even while mixed strategies and beliefs … continue to cycle. This time average is related to the best response cycle first identified by Shapley (1964). For many games …

games learning fails to converge to any equilibrium, either in terms of marginal frequencies or of average play. Subjects … played repeatedly in fixed pairings one of two 3 ´ 3 games, each having a unique Nash equilibrium in mixed strategies. The … equilibrium of one game is predicted to be stable under learning, the other unstable, provided payoffs are sufficiently high. We …

Fictitious play and "gradient" learning are examined in the context of a large population where agents are repeatedly … randomly matched. We show that the aggregation of this learning behaviour can be qualitatively di®erent from learning at the …

Reinforcement learning and stochastic fictitious play are apparent rivals as models of human learning. They embody … general models of stochastic fictitious play and perturbed reinforcement learning have identical local stability properties …. The main identifiable difference between the two models is speed: stochastic fictitious play gives rise to faster learning. …