Equilibrium Learning in Auction Markets
DOI:
https://doi.org/10.1609/aaai.v36i11.21578Keywords:
Learning In Games, Equilibrium Computation, Bayesian Games, Multi-Agent LearningAbstract
My dissertation investigates the computation of Bayes-Nash equilibria in auctions via multiagent learning. A particular focus lies on the game-theoretic analysis of learned gradient dynamics in such markets. This requires overcoming several technical challenges like non-differentiable utility functions and infinite-dimensional strategy spaces. Positive results may open the door for wide-ranging applications in Market Design and the economic sciences.Downloads
Published
2022-06-28
How to Cite
Heidekrüger, S. (2022). Equilibrium Learning in Auction Markets. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12882-12883. https://doi.org/10.1609/aaai.v36i11.21578
Issue
Section
The Twenty - Seventh AAAI / SIGAI Doctoral Consortium