Optimal Auctions through Deep Learning

Dütting, Paul; Feng, Zhe Chuan; Narasimhan, Harikrishna; Parkes, David C.; Ravindranath, Sai Srivatsa

doi:10.48550/arxiv.1706.03459

Cited by 12 publications

(34 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we assume access to a tabular and discrete representation of the counterfactual game and an important future direction is to expand these ideas to more complex multi-agent environments, for example those including multiple steps and planning (Shu and Tian, 2018). Such extensions would naturally require multi-agent learning algorithms that can handle function approximation such as those based on deep learning (Heinrich and Silver, 2016;Dütting et al, 2017;Lowe et al, 2017;Feng et al, 2018;Brown et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

“…For example, they often require the auctioneer to know the distribution of types (valuations) in the population. These strong assumptions are relaxed in robust mechanism design (Bergemann and Morris, 2005), automated mechanism design (Conitzer and Sandholm, 2002), and recent work in using deep learning methods to approximate optimal mechanisms (Dütting et al, 2017;Feng et al, 2018). Optimal mechanism design is related to, but different from, the RMAC problem as it typically assumes access to at least some direct information about the distribution of types, whereas our main problem is to robustly infer the underlying types from observed actions.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Robust Multi-agent Counterfactual Prediction

Peysakhovich,

Kroer,

Lerer

2019

Preprint

View full text Add to dashboard Cite

We consider the problem of using logged data to make predictions about what would happen if we changed the 'rules of the game' in a multi-agent system. This task is difficult because in many cases we observe actions individuals take but not their private information or their full reward functions. In addition, agents are strategic, so when the rules change, they will also change their actions. Existing methods (e.g. structural estimation, inverse reinforcement learning) make counterfactual predictions by constructing a model of the game, adding the assumption that agents' behavior comes from optimizing given some goals, and then inverting observed actions to learn agent's underlying utility function (a.k.a. type). Once the agent types are known, making counterfactual predictions amounts to solving for the equilibrium of the counterfactual environment. This approach imposes heavy assumptions such as rationality of the agents being observed, correctness of the analyst's model of the environment/parametric form of the agents' utility functions, and various other conditions to make point identification possible. We propose a method for analyzing the sensitivity of counterfactual conclusions to violations of these assumptions. We refer to this method as robust multi-agent counterfactual prediction (RMAC). We apply our technique to investigating the robustness of counterfactual claims for classic environments in market design: auctions, school choice, and social choice. Importantly, we show RMAC can be used in regimes where point identification is impossible (e.g. those which have multiple equilibria or non-injective maps from type distributions to outcomes). * Equal contribution, author order has been randomized.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Robust Multi-agent Counterfactual Prediction

Peysakhovich,

Kroer,

Lerer

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…16. The comparison of revenue for the study by Dütting et al [86] According to Fig. 16, RegretNet as the proposed technique increased the revenue by about 2.32 and 2 % compared with VVCA and AMAbsym, respectively.…”

Section: Deep Learning In Auction Mechanismsmentioning

confidence: 98%

“…There are many works with results for single bidders but most often with partial optimality [79][80][81]. Multi-layer neural Network method Auction in mobile network Dütting et al [86] designed a compatible auction with multi-bidder that maximize the profit by applying multi-layer neural networks for encoding its mechanisms. The proposed method was able to solve much more complex tasks while using augmented Lagrangian technique than LP-based approach.…”

Section: Deep Learning In Auction Mechanismsmentioning

confidence: 99%

Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

Mosavi

Ghamisi²,

Faghan³

et al. 2020

SSRN Journal

View full text Add to dashboard Cite

“…Closest to our work are recent approaches for automated mechanism design through machine learning, and deep learning in particular [10,12,23]. These approaches search a family of payment functions for a mechanism with desired properties by defining a loss relating to the desired properties.…”

Section: Related Workmentioning

confidence: 99%

Learning Truthful, Efficient, and Welfare Maximizing Auction Rules

Tacchetti¹,

Strouse²,

Garnelo³

et al. 2019

Preprint

View full text Add to dashboard Cite

Auctions are protocols to allocate goods to buyers who have preferences over them, and collect payments in return. Economists have invested significant effort in designing auction rules that result in allocations of the goods that are desirable for the group as a whole. However, for settings where participants' valuations of the items on sale are their private information, the rules of the auction must deter buyers from misreporting their preferences, so as to maximize their own utility, since misreported preferences hinder the ability for the auctioneer to allocate goods to those who want them most. Manual auction design has yielded excellent mechanisms for specific settings, but requires significant effort when tackling new domains. We propose a deep learning based approach to automatically design auctions in a wide variety of domains, shifting the design work from human to machine. We assume that participants' valuations for the items for sale are independently sampled from an unknown but fixed distribution. Our system receives a data-set consisting of such valuation samples, and outputs an auction rule encoding the desired incentive structure. We focus on producing truthful and efficient auctions that minimize the economic burden on participants. We evaluate the auctions designed by our framework on well-studied domains, such as multi-unit and combinatorial auctions, showing that they outperform known auction designs in terms of the economic burden placed on participants.

show abstract

Optimal Auctions through Deep Learning

Cited by 12 publications

References 21 publications

Robust Multi-agent Counterfactual Prediction

Robust Multi-agent Counterfactual Prediction

Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

Learning Truthful, Efficient, and Welfare Maximizing Auction Rules

Contact Info

Product

Resources

About