Efficient learning equilibrium

By Ronen I. Brafman, Moshe Tennenholtz. 2004

90 citations recorded by the source corpus.

Subfields: Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

Citations in the corpus

Learning with Opponent-Learning Awareness (2017, background): “Brafman and Tennenholtz (2003) introduce the concept of an ‘efﬁcient learning equilibrium’ (ELE), in which neither side is encouraged to deviate from the learning rule.”
AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents (2003, methodology): “The notion of Efficient Learning Equilibrium ( Brafman & Tennenholtz, 2004, 2005 ) has been proposed as an alternative to the use of prior distributions over either the game being played or the opponents’ strategies.”
Multi-Agent Reinforcement Learning:a critical survey (2003, background): “Although one could have expected a game theory purist to adopt this perspective, it is not one studied in game theory, and in fact is explicitly rejected in at least one place [Fudenberg and Kreps1993]; we have only seen it pursued recently, outside game theory [Tennenholtz2002].”
If multi-agent learning is the answer, what is the question? (2007, background): “In fact, the only example we know originates in AI rather than game theory [9], and it is explicitly rejected by at least some game theorists [18].”
New Criteria and a New Algorithm for Learning in Multi-Agent Systems (2004, background): “This problem is directly addressed in [2] and a counter-proposal made for how to consider equilibria in repeated games.”
Cooperative Multi-Agent Learning: The State of the Art (2005, methodology): “Researchers have argued that an important part of cooperative multiagent learning is figuring out how to adjust the learning methods or the problem domain such that the agents are likely to converge to desired Nash equilibria, especially ones which are near-optimal [241, 31, 260].”
Learning against multiple opponents (2006, background): “) Brafman and Tennenholtz addressed this problem directly in [4] and made a counter-proposal for how to consider equilibria in repeated games.”
Performance Bounded Reinforcement Learning in Strategic Interactions (2004, background): “This is Efficient Learning Equilibrium (ELE) (Brafman & Tennenholtz 2002a), where the players’ learning algorithms are required to reach an equilibrium in polynomial time, but which may not exist under imperfect monitoring settings.”