FUDENBERG,D.andKREPS, D. M. (1993). Learning mixed equilibria. Games Econom. Behav. 5 320--367. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Time to Absorption in Discounted Reinforcement Models - Pemantle, Skyrms (2003) (Correct)
.... collective learning takes place in the form of network formation or adaptation of strategies: sociologists studying the small world network phenomenon [WS98, BW00] formation of dyads of reciprocal approval [FM96] economists studying evolutionary game theory [MS82] strategic learning [RE95] [FK93] or its interaction with network structure [Ell93, AI97] These models are designed to explore mechanisms by which agents with limited information, rationality or sophistication may nevertheless achieve advantageous social structures via the application of simple rules for behavior change. Due, ....
Fudenberg, D. and Kreps, K. (1993). Learning mixed equilibria. Games and Econ. Beh. 5, 320-367.
Cognition And Behavior In Normal-Form Games: An.. - Costa-Gomes, Crawford, .. (1998) (1 citation) (Correct)
.... models vary greatly in their assumptions about sophistication, ranging from reinforcement learning (Roth and Erev (1995) in which players need not even know that they are playing a game, to models in which players have complete models of the structure but simplified models of others decisions (Fudenberg and Kreps (1993), Crawford (1995) Crawford and Broseta (1998) Ho, Camerer, and Weigelt (1998) Camerer and Ho (1998) and models whose cognitive requirements approach those of the deductive rationale for equilibrium (Kalai and Lehrer (1993) Stahl (1996) Even the least sophisticated among these learning ....
Fudenberg, Drew, and David Kreps (1993): "Learning Mixed Equilibria," Games and Economic Behavior, 5, 320-367.
Reputation versus Social Learning - Jackson, Kalai (1999) (Correct)
....to converge to approximate the Nash equilibrium of the realized types, no matter how small is. This idea of building on Harsanyi s purification theorem and studying the consolidated behavior of nearby types has been used before in other learning models; and in particular Fudenberg and Kreps [7] use it in studying fictitious play. The indirect contributions of this paper to rational learning are similar to, yet different from, some existing papers. First, like Jordan [12,14] and 5 Jackson and Kalai [14] this paper is restricted to learning Nash equilibrium within the play of Bayesian ....
Fudenberg, D. and D. Kreps [1993], " Learning Mixed Equilibria," Games and Economic Behavior, Vol. 5, pp. 320-368.
Evolution Through Imitation in a Single Population - Levine, Pesendorfer (2000) (Correct)
....stable set is not Nash and gives players less than the minmax as well. However, implicit in this formulation is that mixing takes places by accident, through half of the population doing one thing and half something else. It is fairly well known in the learning literature, for example from Fudenberg and Kreps [1993], that this can be problematic. However, we can also consider mixing through explicit randomization: that is, introduce a mixed strategy as an explicit pure strategy. Suppose that we do this in the example: we add a strategy of randomizing 50 50 between Hunt and Gather. It is apparent that if half ....
Fudenberg, D. and D. Kreps [1993]: "Learning Mixed Equilibria," Games and Economic Behavior, 5: 320-367.
Evolution and Equilibrium under Inexact Information - Sandholm (Correct)
....While at interior equilibria, local probabilistic stability accords closely with standard deterministic notions of stability, it is significantly less demanding at equilibria which lie on the boundary. It is useful to contrast the model studied here with models of stochastic fictitious play (Fudenberg and Kreps (1993), Kaniovski and Young (1995) Benam and Hirsch (1996) These models consider small groups of players who repeatedly play a normal form game. Players choose best responses to their recollections of the history of play. Suppose that payoffs are noisy, or that players recollections of the history ....
Fudenberg, D., and D. M. Kreps (1993). "Learning Mixed Equilibria," Games and Economic Behavior 5, 320-367.
Multiagent Cooperative Search for Portfolio Selection - Parkes, Huberman (2 citations) (Correct)
....game theory shares our assumption of bounded rational agents. Bounded rational learning in games suggests simple best response dynamics in repeated games as an alternative to computing equilibrium solutions directly, and investigates the solution concepts that are supported at equilibrium (Fudenberg and Kreps, 1993; Kandori et al. 1993) Most models assume that agents play best response to a model of the other agents (model based learning) for example Fictitious Play (Fudenberg and Kreps, 1993) and other models of myopic best response dynamics (Young, 1993; Kandori et al. 1993) A common assumption, ....
.... computing equilibrium solutions directly, and investigates the solution concepts that are supported at equilibrium (Fudenberg and Kreps, 1993; Kandori et al. 1993) Most models assume that agents play best response to a model of the other agents (model based learning) for example Fictitious Play (Fudenberg and Kreps, 1993), and other models of myopic best response dynamics (Young, 1993; Kandori et al. 1993) A common assumption, that is used to justify myopic play, is that agents play a random matching game in a stationary environment, which ignores the possibility that other agents in the game might also adapt ....
[Article contains additional citation context not shown here]
Fudenberg, D., and Kreps, D. M. (1993). "Learning mixed equilibria," Games Econ. Behav. 5, 320--367.
Learning and Adaption in Multiagent Systems - David Parkes (Correct)
....the agents will receive in every outcome of the game. For example, agent 1 and agent 2 will receive payoffs of 4 and 2 respectively at the outcome (D; R) The only pure Nash equilibrium in this game is the strategy profile (U; M ) This strategy profile can easily be learned with fictitious play (Fudenberg Kreps 1993). The problem with fictitious play is that we cannot expect convergence to a pure strategy, even when one exists. Consider game (b) in figure 1. The only change from game (a) is that the payoff of agent 2 in the outcome (U; M) has been changed from 4.7 to 4. The result of fictitious play is a ....
Fudenberg, D., and Kreps, D. M. 1993. Learning mixed equilibria. Games and Economic Behavior 5:320--367.
Convergent Multiple-Timescales Reinforcement Learning.. - Leslie, Collins (2003) (Correct)
No context found.
FUDENBERG,D.andKREPS, D. M. (1993). Learning mixed equilibria. Games Econom. Behav. 5 320--367.
Belief Affirming in Learning Processes - Monderer, Samet, Sela (1997) (3 citations) (Correct)
No context found.
D. Fudenberg and D. Kreps, Learning mixed equilibria, Games Econ. Behav. 5 (1993), 320#367.
Random Processes with Reinforcement - Pemantle (Correct)
No context found.
Fudenberg, D. and Kreps, K. (1993). Learning mixed equilibria. Games and Econ. Beh. 5, 320-367.
Nonparametric Adaptive Learning with Feedback - Chen (1994) (Correct)
No context found.
Fudenberg, D. and D.M. Kreps (1993): "Learning Mixed Equilibria," Games and Economic Behavior, 5, 320-367.
On the Indices of Zeros of Nash Fields - DeMichelis, Germano (2000) (1 citation) (Correct)
No context found.
Fudenberg, D. and D.M. Kreps (1993) "Learning Mixed Equilibria," Games and Economic Behavior, 5: 320-367.
Normal Behavior, Altruism and Aggression in Cooperative Game.. - Kleimenov, al. (1998) (Correct)
No context found.
Fudenberg, D., and Kreps, D. M., 1993, Learning mixed equilibria, Games and Econ. Behavior, V. 5, 320-367.
Asynchronous Choice and Markov Equilibria: Theoretical.. - Bhaskar, Vega-Redondo (Correct)
No context found.
Fudenberg, D. & D. Kreps (1993): "Learning mixed equilibria", Games and Economic Behavior 5, 320-67.
Dynamic Model of Market of Patents and Equilibria in.. - Kryazhimskii, Watanabe (2000) (Correct)
No context found.
Fudenberg, D., and Krebs, D.M., 1993, Learning mixed equilibria, Games and Econ. Behavior, Vol. 5, 320-367.
The Evolution of Cooperation Through Imitation - David Levine And (Correct)
No context found.
Fudenberg, D. and D. Kreps [1993]: "Learning Mixed Equilibria," Games and Economic Behavior, 5: 320-367.
Searching Market Equilibria under Uncertain Utilities - Kryazhimskii, Nentjes.. (1998) (2 citations) (Correct)
No context found.
Fudenberg, D., Kreps, D.M., 1993, Learning Mixed Equilibria, Games and Econ. Behavior, Vol. 5, 320-367.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC