Rational Learning Leads to Nash Equilibrium

Kalai, Ehud; Lehrer, Ehud

doi:10.2307/2951492

Cited by 562 publications

(341 citation statements)

References 31 publications

Supporting

Mentioning

329

Contrasting

Unclassified

Order By: Relevance

“…This means that players' learning induced predictions concerning the play path will match the distribution over play paths induced by the true (realized) distribution over types. This second result can be obtained almost directly from a learning result in Kalai and Lehrer (1993). It means that in late games, any discrepancy between the true and the learning induced type generating distributions cannot be detected, even with sophisticated statistical tests.…”

Section: Introductionmentioning

confidence: 89%

See 1 more Smart Citation

Recurring Bullies, Trembling and Learning

Jackson

Kalai

1997

Understanding Strategic Interaction

Self Cite

View full text Add to dashboard Cite

Abstract. In a recurring game, a stage game is played consecutively by di erent groups of players, with each group receiving information about the play of earlier groups. Starting with uncertainty about the distribution of types in the population, late groups may learn to play a correct Bayesian equilibrium, as if they know the type distribution. This paper concentrates on Selten's Chain Store game and the Kreps, Milgrom, Roberts, Wilson phenomenon, where a small perceived inaccuracy about the type distribution can drastically alter the equilibrium behavior. It presents su cient conditions that prevent this phenomenon from persisting in a recurring setting.

show abstract

Section: Introductionmentioning

confidence: 89%

“…Proposition 2 can be proven using Proposition 1, or can be seen more directly as a consequence of Theorem 3 in Kalai and Lehrer (1993). 8 With the xed stage game strategies, let be the probability distribution induced on the stage game play paths by the real prior, , and let~ be the one induced by the assumed prior, t .…”

Section: Social Learningmentioning

confidence: 99%

Recurring Bullies, Trembling and Learning

Jackson

Kalai

1997

Understanding Strategic Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…Yet a little is known about the process by which players learn if they do. Recent papers by J. S. Jordan [4] and E. Kalai and E. Lehrer [5] indicate increasing interest in the mutual learning processes in Bayesian games which leads to Bayesian equilibrium.…”

Section: Main Theorem the Players' Predictions About The Other Playementioning

confidence: 99%

Communication Leading to Nash Equilibrium without Acyclic Condition

Matsuhisa

2004

Computational Science - ICCS 2004

View full text Add to dashboard Cite

Abstract.A pre-play communication-process is presented which leads to a Nash equilibrium of a strategic form game. In the communication process each player predicts the other players' actions, and he/she communicates privately his/her conjecture through message according to a protocol. All the players receiving the messages learn and revise their conjectures. We show that after a long round of the communication the profile of players' conjectures in the revision process leads a mixed strategy Nash equilibrium of the game.

show abstract

“…The importance of learning in negotiation has been recently recognized in the game research community as fundamental for understanding human behavior as well as for developing new solution concepts Osborne & Rubinstein 1994, Jordan 1992, Kalai & Lehrer 1993 . Theoretical results most of which are partial and preliminary , however, are available only for the simplest game settings.…”

Section: Learning In Negotiationmentioning

confidence: 99%

“…& Zlotkin 1994, Osborne & Rubinstein 1994 deals with coordination and negotiation issues by giving pre-computed solutions to speci c problems. There has been much research reported on developing theoretical models in which learning plays an eminent role, especially in the area of adaptive dynamics of games e.g., Jordan 1992, Kalai & Lehrer 1993 . However, to build autonomous agents that improve their negotiation competence based on learning from their interactions with other agents is still an emerging area.…”

Section: Introductionmentioning

confidence: 99%

How can an agent learn to negotiate?

Zeng

Sycara

1997

Intelligent Agents III Agent Theories, Architectures, and Languages

View full text Add to dashboard Cite

Negotiation has been extensively discussed in game-theoretic, economic, and management science literatures for decades. Recent growing interest in autonomous interacting software agents and their potential application in areas such as electronic commerce has given increased importance to automated negotiation. Evidence both from theoretical analysis and from observations of human interactions suggests that if decision makers can somehow take i n to consideration what other agents are thinking and furthermore learn during their interactions how other agents behave, their payo might increase. In this paper, we propose a sequential decision making model of negotiation, called Bazaar. It provides an adaptive, multi-issue negotiation model capable of exhibiting a rich set of negotiation behaviors. Within the proposed negotiation framework, we model learning as a B a yesian belief update process. In this paper, we present both theoretical analysis and initial experimental results showing that learning is bene cial in the sequential negotiation model.

show abstract

Rational Learning Leads to Nash Equilibrium

Cited by 562 publications

References 31 publications

Recurring Bullies, Trembling and Learning

Recurring Bullies, Trembling and Learning

Communication Leading to Nash Equilibrium without Acyclic Condition

How can an agent learn to negotiate?

Contact Info

Product

Resources

About