Economic reasoning and artificial intelligence

DC Parkes, MP Wellman - Science, 2015 - science.org
The field of artificial intelligence (AI) strives to build rational agents capable of perceiving the
world around them and taking actions to advance specified goals. Put another way, AI …

Open problems in cooperative ai

A Dafoe, E Hughes, Y Bachrach, T Collins… - arxiv preprint arxiv …, 2020 - arxiv.org
Problems of cooperation--in which agents seek ways to jointly improve their welfare--are
ubiquitous and important. They can be found at scales ranging from our daily routines--such …

The ai economist: Improving equality and productivity with ai-driven tax policies

S Zheng, A Trott, S Srinivasa, N Naik… - arxiv preprint arxiv …, 2020 - arxiv.org
Tackling real-world socio-economic challenges requires designing and testing economic
policies. However, this is hard in practice, due to a lack of appropriate (micro-level) …

Optimal auctions through deep learning

P Dütting, Z Feng, H Narasimhan… - International …, 2019 - proceedings.mlr.press
Designing an incentive compatible auction that maximizes expected revenue is an intricate
task. The single-item case was resolved in a seminal piece of work by Myerson in 1981 …

Optimal-er auctions through attention

D Ivanov, I Safiulin, I Filippov… - Advances in Neural …, 2022 - proceedings.neurips.cc
RegretNet is a recent breakthrough in the automated design of revenue-maximizing
auctions. It combines the flexibility of deep learning with the regret-based approach to relax …

[PDF][PDF] Deep learning for revenue-optimal auctions with budgets

Z Feng, H Narasimhan… - Proceedings of the 17th …, 2018 - econcs.seas.harvard.edu
The design of revenue-maximizing auctions for settings with private budgets is a hard task.
Even the single-item case is not fully understood, and there are no analytical results for …

[PDF][PDF] Deep Learning for Multi-Facility Location Mechanism Design.

N Golowich, H Narasimhan, DC Parkes - IJCAI, 2018 - econcs.seas.harvard.edu
Abstract Moulin [1980] characterizes the single-facility, deterministic strategy-proof
mechanisms for social choice with single-peaked preferences as the set of generalized …

Breaking the traditional: a survey of algorithmic mechanism design applied to economic and complex environments

Q Chen, X Wang, ZL Jiang, Y Wu, H Li, L Cui… - Neural Computing and …, 2023 - Springer
The mechanism design theory can be applied not only in the economy but also in many
fields, such as politics and military affairs, which has important practical and strategic …

Auction learning as a two-player game

J Rahme, S Jelassi, SM Weinberg - arxiv preprint arxiv:2006.05684, 2020 - arxiv.org
Designing an incentive compatible auction that maximizes expected revenue is a central
problem in Auction Design. While theoretical approaches to the problem have hit some …

A permutation-equivariant neural network architecture for auction design

J Rahme, S Jelassi, J Bruna… - Proceedings of the AAAI …, 2021 - ojs.aaai.org
Designing an incentive compatible auction that maximizes expected revenue is a central
problem in Auction Design. Theoretical approaches to the problem have hit some limits in …