Equilibrium Points in N-Person Games.

By J. Nash. 1950

How researchers see this paper

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

In Game & Decision Theory

Citations in the corpus

DeepStack: Expert-level artificial intelligence in heads-up no-limit poker (2017, background): “In two-player zero-sum games, like HUNL, a solution or Nash equilibrium strategy (23) maximizes the expected utility when playing against a best-response opponent strategy.”
Optimal and Approximate Q-value Functions for Decentralized POMDPs (2008, background): “Nash (1950) proved that when allowing mixed policies, every (finite) strategic game contains at least one NE, making it a proper solution for a game.”
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “The first one is called Nash equilibrium (Nash, 1950; Osborne & Rubinstein, 1994).”
Multiagent learning using a variable learning rate (2002, background): “The transition function defines a probability distribution over next states as a function of the current state and the agent’s action.”
An Online Learning Approach to Generative Adversarial Networks (2017, background): “Standard GAN approaches aim at ﬁnding a pure Nash Equilibrium by using traditional gradient-based techniques to minimize each player’s cost in an alternating fashion.”
If MaxEnt RL is the Answer, What is the Question? (2019, background): “We recall that the Nash Existence Theorem [33] proves that a Nash Equilibrium will always exist.”
Games of incomplete information, ergodic theory, and the measurability of equilibria (2003, background): “define the game Fi to be that played on the set Si := {sl,..., si} with the players 3~ := {d E fll v(J) n Si¢ ~} and the probability distributions p~ on Si (for the players in fli) induced by p~(B) := pJ(B)/pJ(Si) for all B C_ Si- Since each Si and Si are finite, there exists a Nash equilibrium fi :”
Re-evaluating evaluation (2018, background): “A problem with Nash equilibria (NE) is that they are not unique, which forces the user to make choices and undermines interpretability [63,64].”
The free-energy principle: a unified brain theory? (2010, background): “Cost also has a key role in Bayesian decision theory, in which optimal decisions minimize expected cost in the context of uncertainty about outcomes; this is central to optimal decision theory (game theory) and behavioural economic”