# Calibrated Learning and Correlated Equilibrium

@article{Foster1996CalibratedLA, title={Calibrated Learning and Correlated Equilibrium}, author={Dean P. Foster and Rakesh V. Vohra}, journal={Games and Economic Behavior}, year={1996}, volume={21}, pages={40-55} }

Abstract Suppose two players repeatedly meet each other to play a game where 1. each uses a learning rule with the property that it is a calibrated forecast of the other's plays, and 2. each plays a myopic best response to this forecast distribution. Then, the limit points of the sequence of plays are correlated equilibria. In fact, for each correlated equilibrium there is some calibrated learning rule that the players can use which results in their playing this correlated equilibrium in the… Expand

#### 356 Citations

A Reinforcement Procedure Leading to Correlated Equilibrium

- Mathematics
- 2001

We consider repeated games where at any period each player knows only his set of actions and the stream of payoffs that he has received in the past. He knows neither his own payoff function, nor the… Expand

Learning correlated equilibria: An evolutionary approach

- Economics
- 2016

Abstract Correlated equilibrium ( Aumann, 1974 , Aumann, 1987 ) is an important generalization of the Nash equilibrium concept for multiplayer non-cooperative games. In a correlated equilibrium,… Expand

Learning in Games with Cumulative Prospect Theoretic Preferences

- Mathematics, Computer Science
- Dynamic Games and Applications
- 2021

It is shown that, when the players have calibrated strategies and behave according to CPT, the natural analog of the notion of correlated equilibrium in the CPT case, as defined by Keskin, is not enough to capture all subsequential limits of the empirical distribution of action play. Expand

Selecting efficient correlated equilibria through distributed learning

- Computer Science, Economics
- Games Econ. Behav.
- 2017

A simple, completely uncoupled learning rule is demonstrated such that, in any finite normal form game with generic payoffs, the players' realized strategies implements a socially optimal coarse correlated (Hannan) equilibrium a very high proportion of the time. Expand

Learning and Equilibrium

- Economics
- 2009

The theory of learning in games explores how, which, and what kind of equilibria might arise as a consequence of a long-run nonequilibrium process of learning, adaptation, and/or imitation. If… Expand

Learning to Play Equilibria: The Bayesian, Repeated Games Approach∗

- Computer Science
- 2004

This is a survey of the last 15 years or so of research into an important class of models of how players might come to play equilibria in games: Bayesian models of learning in repeated strategic form… Expand

Correlated Equilibrium, Public Signaling and Absorbing Games

- Mathematics
- 1999

An absorbing game is a repeated game where some of the action combinations are absorbing, in the sense that whenever they are played, there is a positive probability that the game terminates, and the… Expand

Deterministic calibration and Nash equilibrium

- Computer Science, Mathematics
- J. Comput. Syst. Sci.
- 2008

A natural learning process in which the joint frequency of empirical play converges into the set of convex combinations of Nash equilibria, and it is shown that such a deterministic (weakly) calibrated learning algorithm exists. Expand

Selecting efficient correlated equilibria through distributed learning

- Computer Science
- 2015 American Control Conference (ACC)
- 2015

A simple, completely uncoupled learning rule is demonstrated such that, in any finite normal form game with generic payoffs, the players' realized strategies implements a Pareto optimal coarse correlated (Hannan) equilibrium a very high proportion of the time. Expand

Correlated equilibrium payoffs and public signalling in absorbing games

- Economics, Computer Science
- Int. J. Game Theory
- 2002

It is proved that every multi-player absorbing game admits a correlated equilibrium payoff, that is, for every ε>0 there exists a probability distribution pε over the space of pure strategy profiles that satisfies the following. Expand

#### References

SHOWING 1-10 OF 30 REFERENCES

Adaptive and sophisticated learning in normal form games

- Mathematics
- 1991

Abstract In a class of games including some Cournot and Bertrand games, a sequence of plays converges to the unique Nash equilibrium if and only if the sequence is “consistent with adaptive learning”… Expand

Correlated Equilibrium as an Expression of Bayesian Rationality Author ( s )

- Economics, Mathematics
- 1987

If it is common knowledge that the players in a game are Bayesian utility maximizers who treat uncertainty about other players' actions like any other uncertainty, then the outcome is necessarily a… Expand

Subjective Games and Equilibria

- Economics, Computer Science
- 1993

The proposed notions of subjective games and of subjective Nash and correlated equilibria replace essential but unavailable objective knowledge by subjective assessments when playing a subjective game repeatedly, subjective optimizers converge to a subjective equilibrium. Expand

Coherent behavior in noncooperative games

- Mathematics
- 1990

Abstract A new concept of mutually expected rationality in noncooperative games is proposed: joint coherence. This is an extension of the “no arbitrage opportunities” axiom that underlies subjective… Expand

CORRELATED EQUILIBRIUM AS AN EXPRESSION OF

- Mathematics
- 1987

Correlated equilibrium is formulated in a manner that does away with the dichotomy usually perceived between the "Bayesian" and the "game-theoretic" view of the world. From the Bayesian viewpoint,… Expand

A simple adaptive procedure leading to correlated equilibrium

- Mathematics
- 1997

We propose a new and simple adaptive procedure for playing a game: ‘‘regret-matching.’’ In this procedure, players may depart from their current play with probabilities that are proportional to… Expand

ON THE CONVERGENCE OF THE LEARNING PROCESS IN A 2 X 2 NON-ZERO-SUM TWO-PERSON GAME

- Mathematics
- 1961

Abstract : A problem is presented as follows: Will a learning process give rise to an equilibrium point; that is, will a seque ce of mixed stra egies xk yk oci i a le rning process converge to… Expand

An analog of the minimax theorem for vector payoffs.

- Mathematics
- 1956

for all i, j . Thus in the (two-person, zero-sum) game with matrix Λf, player I has a strategy insuring an expected gain of at least v, and player II has a strategy insuring an expected loss of at… Expand

Evolutionary Stability in Asymmetric Games

- Economics
- 1992

We examine dynamic models of evolutionary selection processes on asymmetric two-player games. Conditions are established under which dynamic selection processes will yield outcomes that respect… Expand

SOME TOPICS IN TWO-PERSON GAMES

- Mathematics
- 1963

Abstract : Several loosely-related essays on the theory of finite, two-person games are presented. The topics covered are: (1) the block decomposition of symmetric games; (2) saddle points in… Expand