CPSC 540: Machine Learning
Using Sampling To Compute Bayes-Nash Equilibrium In Auction Games
Project report:
pdf,
ps.gz
Source code:
tar.gz
Abstract
The use of sampling is investigated for computing equilibrium bidding
strategies in auctions. An algorithm is proposed that requires
minimal assumptions on the agents. In this paper we concentrate on
asymmetric auctions with independent bidder valuations, however the
approach is extendable to other scenarios, for example having bidders
with different risk attitudes. Results are presented and the
performance of the algorithm is discussed.
| 
