Subjectivity and Correlation in Randomized Strategies

By R. Aumann. 1974

How researchers see this paper

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

Citations in the corpus

MAVEN: Multi-Agent Variational Exploration (2019, background): “Aumann [1] proposes the concept of a correlated equilibrium in non-cooperative multi-agent settings in which each agent conditions its policy on some shared variable that is sampled every episode.”
Multi-Agent Common Knowledge Reinforcement Learning (2018, background): “Aumann et al. (1974) introduce the concept of a correlated equilibrium , whereby a shared correlation device helps agents coordinate better.”
Deep Online Convex Optimization by Putting Forecaster to Sleep (2015, background): “Finally, a closely related line of work, modeling biological neural networks from a game-theoretic perspective, can be found in (Balduzzi and Besserve, 2012; Balduzzi, 2013, 2014; Balduzzi et al., 2015).”
Biform Games (2007, background): “51This is the Preliminary Observation in Aumann and Brandenburger (1995).”
AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents (2003, background): “For instance, one may consider correlated equilibrium (Aumann, 1974), in which the players receive correlated random signals (before playing the stage game), on which they can then base their play.”
Correlated Q-Learning (2003, background): “Correlated- Q learning is named for correlated equilibria (Aumann 1974), which generalize Nash equilibria by allowing for possible dependencies in strategic choices.”
Semi-supervised Learning on Graphs with Generative Adversarial Nets (2018, methodology): “In game theory, it is called myopic best response [1], an effective heuristic method to find equilibriums.”
More than Thirty Years of Ultimatum Bargaining Experiments: Motives, Variations, and a Survey of the Recent Literature (2013, unknown): “As a consequence, the empirical finding of the modal offer / 2y p= seems less troublesome for game theory (see Aumann, 1974, who propagates coarsening rather than refining the equilibrium concept) than the observation that low offers, for example in the region / 3y p , are sufficiently often…”
Efficient learning equilibrium (2004, methodology): “Therefore, the right way to view this party is as a mediator/intersted party or correlation device (as in [1, 9], etc.”
A Reinforcement Procedure Leading to Correlated Equilibrium (2001, unknown): “As in (2), the modified regrets are then Qt (j, k) := [ C t (j, k) ]+ ≡ max {Ci t (j, k) , 0} .”
BAR fault tolerance for cooperative services (2005, background): “Game theory [25] has a long history in the economics literature [4, 28, 41] and has recently become of general interest in computer science [3, 20, 22, 23, 45, 48, 61].”
Game Theory and Multi-agent Reinforcement Learning (2012, background): “These alternatives include a range of other equilibrium concepts, such as the Correlated Equilibrium(CE))(Aumann, 1974), which generalizes the Nash equilibrium concept, or the Evolutionary Stable Strategy (ESS)(Smith, 1982), which refines the Nash equilibrium.”
Game Theory in Wireless and Communication Networks (2008, background): “Furthermore, we note that the set of correlated equilibria is non-empty, closed, and convex in every finite game [47, 48], and may include distributions that are not in the convex hull of the Nash equilibrium solutions.”