Filters








44,084 Hits in 1.9 sec

Learning Simple Auctions [article]

Jamie Morgenstern, Tim Roughgarden
2016 arXiv   pre-print
We present a general framework for proving polynomial sample complexity bounds for the problem of learning from samples the best auction in a class of "simple" auctions.  ...  Our results effectively imply that whenever it's possible to compute a near-optimal simple auction with a known prior, it is also possible to compute such an auction with an unknown prior (given a polynomial  ...  auction from these classes of simple auctions.  ... 
arXiv:1604.03171v1 fatcat:vmrbvrkk7jgbbhr3d5gw2ubtrm

Artificial Intelligence and Auction Design

Martino Banchio, Andrzej Skrzypacz
2022 Proceedings of the 23rd ACM Conference on Economics and Computation  
Motivated by online advertising auctions, we study auction design in repeated auctions played by simple Artificial Intelligence algorithms (Q-learning).  ...  We find that first-price auctions with no additional feedback lead to tacit-collusive outcomes (bids lower than values), while second-price auctions do not.  ...  The simple AI algorithm we use in this paper is Q-learning, one of the most popular algorithms for agnostic learning.  ... 
doi:10.1145/3490486.3538244 fatcat:cmrue32vwvfaxolx3mccb3dbdi

IMPROVING STUDENTS' UNDERSTANDING ON SIMPLE PRESENT TENSE THROUGH AUCTION GRAMMAR GAME AT THE EIGHTH GRADE STUDENTS OF SMP KATOLIK BELIBIS MAKASSAR

Adriani Jihad
2021 ETERNAL (English Teaching Journal)  
It can be concluded that the Auction grammar game improves students' understanding on simple present tense.  ...  This research aimed to find out the Auction Grammar Game in improving students' understanding on simple present tense. This research used pre-experimental method.  ...  It concluded that the students enjoyed the learning process when the researcher using Auction Grammar Game in teaching Simple Present Tense.  ... 
doi:10.26877/eternal.v12i1.8300 fatcat:hjcx4pmi2rbzffse2stltyhrwi

Artificial Intelligence and Auction Design [article]

Martino Banchio, Andrzej Skrzypacz
2022 arXiv   pre-print
Motivated by online advertising auctions, we study auction design in repeated auctions played by simple Artificial Intelligence algorithms (Q-learning).  ...  We find that first-price auctions with no additional feedback lead to tacit-collusive outcomes (bids lower than values), while second-price auctions do not.  ...  The simple AI algorithm we use in this paper is Q-learning, one of the most popular algorithms for agnostic learning.  ... 
arXiv:2202.05947v1 fatcat:pdnxp76j6jby7gxbeughh6fc3u

Bidding agents for online auctions with hidden bids

Albert Xin Jiang, Kevin Leyton-Brown
2006 Machine Learning  
When bidders' valuation distributions are not known ex ante, machine learning techniques can be used to approximate them from historical data.  ...  It is a characteristic feature of auctions, however, that information about some bidders' valuations is systematically concealed.  ...  We tested four learning approaches: the EM and simple approaches that estimate a Normal distribution for f (x) and a Poisson distribution for g(m), and the EM and simple approaches that use kernel density  ... 
doi:10.1007/s10994-006-0477-8 fatcat:gu5lx22tnfcnfbjnytkuq3ogey

Learn to Play Maximum Revenue Auction

Xiaotie Deng, Tao Xiao, Keyu Zhu
2020 Computer  
Machine learning, in another direction, has naturally been utilized to learn the underlying value distributions of customers for better mechanism designs.  ...  As long as the auction and learning algorithm are specified, individual agents will respond to the auction protocol and auctioneer's learning strategy and submit their strategic bids, which may or may  ...  For the manipulation performed by individual agents, we consider the simple and natural strategy space where the agents can manipulate over the parameters.  ... 
doi:10.1109/mc.2020.2981988 fatcat:476u36gfsfgvvcvcgru6haylem

No-Regret Learning from Partially Observed Data in Repeated Auctions

Orcun Karaca, Pier Giuseppe Sessa, Anna Leidi, Maryam Kamgarpour
2020 IFAC-PapersOnLine  
Moreover, we propose a heuristic method for auction settings where the proposed algorithm is not directly applicable.  ...  We study a general class of repeated auctions, such as the ones found in electricity markets, as multi-agent games between the bidders.  ...  Auctions with Simple Constraints and Convex Bids We consider a simpler auction problem where the auctioneer has to procure a fixed amount Q ∈ R + of a single type of good.  ... 
doi:10.1016/j.ifacol.2020.12.029 fatcat:qhlmmpeizjci3dmadlhn2ian3i

Game Theory Meets Computational Learning Theory (Dagstuhl Seminar 17251)

Paul W. Goldberg, Yishay Mansour, Paul Dütting, Marc Herbstritt
2017 Dagstuhl Reports  
This report documents the program and the outcomes of Dagstuhl Seminar 17251 "Game Theory Meets Computational Learning Theory".  ...  While there have been many Dagstuhl seminars on various aspects of Algorithmic Game Theory, this was the first one to focus on the emerging field of its intersection with computational learning theory.  ...  We study simple best-response dynamics.  ... 
doi:10.4230/dagrep.7.6.68 dblp:journals/dagstuhl-reports/GoldbergMD17 fatcat:ca4mfrf3qbdbhhbo7rvc53myti

On the Pseudo-Dimension of Nearly Optimal Auctions

Jamie Morgenstern, Tim Roughgarden
2015 Neural Information Processing Systems  
We introduce t-level auctions to interpolate between simple auctions, such as welfare maximization with reserve prices, and optimal auctions, thereby balancing the competing demands of expressivity and  ...  This paper develops a general approach, rooted in statistical learning theory, to learning an approximately revenue-maximizing auction from data.  ...  That is, we seek a set C that is rich enough to contain an auction that closely approximates an optimal auction (whatever F might be), yet simple enough that the best auction in C can be learned from a  ... 
dblp:conf/nips/MorgensternR15 fatcat:zoadxvn5dbhg3l4o34kqqscnvu

The Effectiveness of Experiential Learning in a Large Classroom: An Example of the Auction Market

Alina M. Zapalska, Dallas Brozik
2020 International Journal for Cross-Disciplinary Subjects in Education  
The research work in this paper presents an experiential learning activity for a large classroom where students take roles of travel agents to learn how a travel agency functions in an auction market.  ...  This auction market has been designed for a large classroom where students learn through experience and discovery in competitive business environment.  ...  outcomes, in-class activities, and assessment requirements), plan on a page (preparation requires planning for content, process, and logistics), and keep it simple (the learning outcomes must be simple  ... 
doi:10.20533/ijcdse.2042.6364.2020.0521 fatcat:fdksdjyp5za6hlyxz3a7ztivre

Learning in a "Basket of Crabs": An Agent-Based Computational Model of Repeated Conservation Auctions [chapter]

Atakelty Hailu, Steven Schilizzi
2005 Lecture notes in economics and mathematical systems  
This study constructs an agentbased model to evaluate the long term performance of conservation auctions under settings where bidders are allowed to learn from previous outcomes.  ...  Auctions are increasingly being considered as a mechanism for allocating conservation contracts to private landowners.  ...  This study conducts a simple agent-based computational experiment to assess the performance of repeated auctions under circumstances where the bidders learn from previous experience.  ... 
doi:10.1007/3-540-27296-8_3 fatcat:wbi7ypa3jbgjzfhvfh7fjobdle

Simple Auctions with Simple Strategies

Nikhil Devanur, Jamie Morgenstern, Vasilis Syrgkanis, S. Matthew Weinberg
2015 Proceedings of the Sixteenth ACM Conference on Economics and Computation - EC '15  
Contrary to other simple auction formats, such as simultaneous or sequential single-item auctions, bidders can implement no-regret learning strategies for single-bid auctions in polynomial time.  ...  Price of anarchy bounds for correlated equilibria concepts in single-bid auctions therefore have more bite than their counterparts for auctions and equilibria for which learning is not known to be computationally  ...  This realization motivates the search for auctions with a simple design that are also strategically simple and have a low price of anarchy.  ... 
doi:10.1145/2764468.2764484 dblp:conf/sigecom/DevanurMSW15 fatcat:gdtldawxjncz3fhn76qbmzwbv4

Approximately Optimal Mechanism Design: Motivation, Examples, and Lessons Learned [article]

Tim Roughgarden
2014 arXiv   pre-print
The first part describes the approximately optimal mechanism design paradigm --- how it works, and what we aim to learn by applying it.  ...  Our goal is to understand if complexity --- in the sense of detailed distributional knowledge --- is an essential feature of good auctions for this problem, or alternatively if there are simpler auctions  ...  We also learned that, in some cases, selling items separately with first-price auctions achieves the best-possible worstcase approximation guarantee of any family of simple mechanisms.  ... 
arXiv:1406.6773v1 fatcat:5czubehre5aqtgh3werd25cqxe

The Price of Anarchy in Auctions

Tim Roughgarden, Vasilis Syrgkanis, Eva Tardos
2017 The Journal of Artificial Intelligence Research  
extend such guarantees from simpler to more complex auctions.  ...  and deterministic strategies; extension theorems, which extend such guarantees to randomized strategies, no-regret learning outcomes, and incomplete-information settings; and composition theorems, which  ...  of any simple auction.  ... 
doi:10.1613/jair.5272 fatcat:7gcmpshgivh2vj4xu2enqe3nue

The Pseudo-Dimension of Near-Optimal Auctions [article]

Jamie Morgenstern, Tim Roughgarden
2015 arXiv   pre-print
We introduce t-level auctions to interpolate between simple auctions, such as welfare maximization with reserve prices, and optimal auctions, thereby balancing the competing demands of expressivity and  ...  This paper develops a general approach, rooted in statistical learning theory, to learning an approximately revenue-maximizing auction from data.  ...  That is, we seek a set C that is rich enough to contain an auction that closely approximates an optimal auction (whatever F might be), yet simple enough that the best auction in C can be learned from a  ... 
arXiv:1506.03684v1 fatcat:qyqpz6eujbakjiqfioqbp62r2q
« Previous Showing results 1 — 15 out of 44,084 results