Learning What is Similar: Precedents and Equilibrium Selection

@article{Argenziano2018LearningWI,
  title={Learning What is Similar: Precedents and Equilibrium Selection},
  author={Rossella Argenziano and I. Gilboa},
  journal={HEC Paris Research Paper Series},
  year={2018}
}
We argue that a precedent is important not only because it changes the relative frequency of a certain event, making it positive rather than zero, but also because it changes the way that relative frequencies are weighed. Specifically, agents assess probabilities of future events based on past occurrences, where not all of these occurrences are deemed equally relevant. More similar cases are weighed more heavily than less similar ones. Importantly, the similarity function is also learnt from… Expand
3 Citations
Second-Order Induction: Uniqueness and Complexity
Similarity-Nash Equilibria in Statistical Games

References

SHOWING 1-10 OF 54 REFERENCES
History as a coordination device
Correlated Equilibrium as an Expression of Bayesian Rationality Author ( s )
A Categorical Model of Cognition and Biased Decision Making
Subjectivity and Correlation in Randomized Strategies
Contagion through learning
The chain store paradox
Do Sunspots Matter?
...
1
2
3
4
5
...