Corpus ID: 169032755

Automated Mechanism Design via Neural Networks

@inproceedings{Shen2019AutomatedMD,
  title={Automated Mechanism Design via Neural Networks},
  author={W. Shen and Pingzhong Tang and Song Zuo},
  booktitle={AAMAS},
  year={2019}
}
Using AI approaches to automatically design mechanisms has been a central research mission at the interface of AI and economics. Previous approaches that attempt to design revenue optimal auctions for the multi-dimensional settings fall short in at least one of the three aspects: 1) representation --- search in a space that probably does not even contain the optimal mechanism; 2) exactness --- finding a mechanism that is either not truthful or far from optimal; 3) domain dependence --- need a… Expand
22 Citations

Figures, Tables, and Topics from this paper

Auction learning as a two-player game
Optimal Auctions through Deep Learning
Mechanism Design for Public Projects via Neural Networks
Reinforcement Mechanism Design, with Applications to Dynamic Pricing in Sponsored Search Auctions
Learning in repeated auctions
Reinforcement Learning for Indirect Mechanism Design
Automated Dynamic Mechanism Design
Automated Mechanism Design for Classification with Partial Verification
ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning
...
1
2
3
...

References

SHOWING 1-10 OF 49 REFERENCES
Complexity of Mechanism Design
Optimal Auctions through Deep Learning
Reinforcement Mechanism Design, with Applications to Dynamic Pricing in Sponsored Search Auctions
Reinforcement mechanism design
Reinforcement Mechanism Design for e-commerce
Optimal Auctions for Partially Rational Bidders
Deep Learning for Multi-Facility Location Mechanism Design
...
1
2
3
4
5
...