nach oben

Autonomous Agents and Multi-Agent Systems

Erschienen in:

22.02.2019

Strategic behavior and learning in all-pay auctions: an empirical study using crowdsourced data

verfasst von: Yoram Bachrach, Ian A. Kash, Peter Key, Joel Oren

Erschienen in: Autonomous Agents and Multi-Agent Systems | Ausgabe 1-2/2019

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

We analyze human behavior in crowdsourcing contests using an all-pay auction model where all participants exert effort, but only the highest bidder receives the reward. We let workers sourced from Amazon Mechanical Turk participate in an all-pay auction, and contrast the game theoretic equilibrium with the choices of the humans participants. We examine how people competing in the contest learn and adapt their bids, comparing their behavior to well-established online learning algorithms in a novel approach to quantifying the performance of humans as learners. For the crowdsourcing contest designer, our results show that a bimodal distribution of effort should be expected, with some very high effort and some very low effort, and that humans have a tendency to overbid. Our results suggest that humans are weak learners in this setting, so it may be important to educate participants about the strategic implications of crowdsourcing contests.

Vorheriger Artikel Multi-agent soft constraint aggregation via sequential voting: theoretical and experimental results

Nächster Artikel A probabilistic argumentation framework for reinforcement learning agents

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Nur mit Berechtigung zugänglich

www.topcoder.com, www.codechef.com.

Empirical results do not always exhibit overbidding. Some studies examining all-pay auctions between two players find no overbidding [16, 32], while studies examining auctions between more than two players find significant overbidding [11, 22] (recent work on this contains a more complete discussion [20]). Further, the degree of overbidding depends on the specifics of the contest and domain [7, 12, 19, 25‐27].

We also allowed players to play against a specific friend, but such games were not used for the analysis in this paper.

We note that players who follow the mixed-strategy of the Nash equilibrium are extremely unlikely to be labeled as spammers. The symmetric mixed-strategy under the Nash equilibrium is choosing a bid uniformly at random over the range, making each possible strategy have a very small probability. In particular, for a player who selects bids uniformly at random, the probability of selecting the specific precluded bids in over 25% of the games is very low. This means that our spammer-detection rule is very unlikely to have a “false-positive”, and mistakenly labeling a player who is using the Nash mixed-strategy as a spammer.

Notably, such collusive strategies are predicted by a different game theoretic analysis of this as a repeated game setting, showing another way human behavior differs from idealized mathematical models in crowdsourcing contests.

Note that the uniform distribution over the bids gives an expected number of distinct bids of 70. Shortly, we provide two more precise comparisons with the uniform distribution.

In particular, such settings include auctions, especially when the winner is simply the highest bidder, rather than ones where the probability of winning is higher for the highest bidder [11], and Blotto games [10, 23].

A player who lost the auction can also lower their bid in an attempt to improve the negative utility they incur, but achieving a positive utility requires increasing the bids so as to win the auction.

We have also tried using only the bid difference \(d_{t-1} = x^{bid}_{t-1} - y^{bid}_{t-1}\) as a feature (i.e. using the two features \(W_{t-1}, d_{t-1}\), which achieves \(R^2=0.34\), still lower than the baseline model.

Amann, E., & Leininger, W. (1996). Asymmetric all-pay auctions with incomplete information: The two-player case. Games and Economic Behavior, 14(1), 1–18.MathSciNetMATHCrossRef

Arad, A., & Rubinstein, A. (Jan. 2010). Colonel blottos top secret files. Levine’s Working Paper Archive 814577000000000432, David K. Levine.

Arad, A., & Rubinstein, A. (2012). The 11–20 money request game: A level-k reasoning study. American Economic Review, 102(7), 3561–73.CrossRef

Arora, S., Hazan, E., & Kale, S. (2012). The multiplicative weights update method: A meta-algorithm and applications. Theory of Computing, 8(1), 121–164.MathSciNetMATHCrossRef

Baye, M., Kovenock, D., & Vries, C. D. (1996). The all-pay-auction with complete information. Economic Theory, 8, 291–305.MathSciNetMATHCrossRef

Bennett, J., & Lanning, S. (2007). The netflix prize. In In KDD Cup and Workshop in conjunction with KDD (Vol. 2007, p. 35).

Burkart, M. (1995). Initial shareholdings and overbidding in takeover contests. The Journal of Finance, 50(5), 1491–1515.CrossRef

Byers, J. W., Mitzenmacher, M., & Zervas, G. (2010). Information asymmetries in pay-per-bid auctions: How swoopo makes bank. CoRR, arXiv:abs/1001.0592.

Camerer, C. F. (2011). Behavioral game theory: Experiments in strategic interaction. Princeton: Princeton University Press.MATHCrossRef

10.

Chowdhury, S. M., Kovenock, D., & Sheremeta, R. M. (2013). An experimental investigation of colonel blotto games. Economic Theory, 52(3), 833–861.MathSciNetMATHCrossRef

11.

Davis, D. D., & Reilly, R. J. (1998). Do too many cooks always spoil the stew? An experimental analysis of rent-seeking and the role of a strategic buyer. Public Choice, 95(1–2), 89–115.CrossRef

12.

Dechenaux, E., Kovenock, D., & Sheremeta, R. M. (2015). A survey of experimental research on contests, all-pay auctions and tournaments. Experimental Economics, 18(4), 609–669.CrossRef

13.

DiPalantino, D., & Vojnovic, M. (2009). Crowdsourcing and all-pay auctions. In Proceedings of the 10th ACM conference on Electronic commerce, EC ’09 (pp. 119–128). New York: ACM.

14.

Douceur, J. R. (2002). The sybil attack. In Revised Papers from the First International Workshop on Peer-to-Peer Systems, IPTPS ’01 (pp. 251–260). London: Springer-Verlag.

15.

Erev, I., & Roth, A. E. (1998). Predicting how people play games: Reinforcement learning. American Economic Review, 88, 848–881.

16.

Ernst, C., & Thni, C. (2013) Bimodal bidding in experimental all-pay auctions. Technical report.

17.

Fallucchi, F., Renner, E., & Sefton, M. (2013). Information feedback and contest structure in rent-seeking games. European Economic Review, 64, 223–240.CrossRef

18.

Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.MathSciNetMATHCrossRef

19.

Gao, X. A., Bachrach, Y., Key, P., Graepel, T. (2012) Quality expectation-variance tradeoffs in crowdsourcing contests. In AAAI (pp. 38–44).

20.

Gelder, A., Kovenock, D., & Sheremeta, R. M. (2015). Behavior in all-pay auctions with ties.

21.

Ghosh, A., & McAfee, P. (2012). Crowdsourcing with endogenous entry. In Proceedings of the 21st international conference on World Wide Web WWW ’12 (pp. 999–1008). New York: ACM.

22.

Gneezy, U., & Smorodinsky, R. (2006). All-pay auctions-an experimental study. Journal of Economic Behavior & Organization, 61(2), 255–275.CrossRef

23.

Kohli, P., Kearns, M., Bachrach, Y., Herbrich, R., Stillwell, D., & Graepel, T. (2012). Colonel blotto on facebook: the effect of social relations on strategic interaction. In WebSci (pp. 141–150).

24.

Krishna, V., & Morgan, J. (1997). An analysis of the war of attrition and the all-pay auction. Journal of Economic Theory, 72(2), 343–362.MATHCrossRef

25.

Lev, O., Polukarov, M., Bachrach, Y., & and Rosenschein, J. S. (May 2013). Mergers and collusion in all-pay auctions and crowdsourcing contests. In The Twelfth international joint conference on autonomous agents and multiagent systems (AAMAS 2013). Saint Paul: Minnesota, To appear.

26.

Lewenberg, Y., Lev, O., Bachrach, Y., & Rosenschein, J. S. (2013). Agent failures in all-pay auctions. In Proceedings of the twenty-third international joint conference on artificial intelligence (pp. 241–247). AAAI Press.

27.

Lewenberg, Y., Lev, O., Bachrach, Y., & Rosenschein, J. S. (2017). Agent failures in all-pay auctions. IEEE Intelligent Systems, 32(1), 8–16.CrossRef

28.

Liu, T. X., Yang, J., Adamic, L. A., & Chen, Y. (2011). Crowdsourcing with all-pay auctions: A field experiment on taskcn. Proceedings of the American Society for Information Science and Technology, 48(1), 1–4.

29.

Lugovskyy, V., Puzzello, D., & Tucker, S. (2010). An experimental investigation of overdissipation in the all pay auction. European Economic Review, 54(8), 974–997.CrossRef

30.

Mago, S. D., Samak, A. C., & Sheremeta, R. M. (2016). Facing your opponents: Social identification and information feedback in contests. Journal of Conflict Resolution, 60(3), 459–481.CrossRef

31.

Mash, M., Bachrach, Y., & Zick, Y. (2017). How to form winning coalitions in mixed human-computer settings. In Proceedings of the 26th international joint conference on artificial intelligence (IJCAI) (pp. 465–471).

32.

Potters, J., de Vries, C. G., & van Winden, F. (1998). An experimental examination of rational rent-seeking. European Journal of Political Economy, 14(4), 783–800.CrossRef

33.

Price, C. R., & Sheremeta, R. M. (2011). Endowment effects in contests. Economics Letters, 111(3), 217–219.MathSciNetCrossRef

34.

Price, C. R., & Sheremeta, R. M. (2015). Endowment origin, demographic effects, and individual preferences in contests. Journal of Economics & Management Strategy, 24(3), 597–619.CrossRef

35.

Sheremeta, R. M., & Zhang, J. (2010). Can groups solve the problem of over-bidding in contests? Social Choice and Welfare, 35(2), 175–197.MathSciNetMATHCrossRef

36.

Stahl, D. O., & Wilson, P. W. (1995). On players models of other players: Theory and experimental evidence. Games and Economic Behavior, 10(1), 218–254.MathSciNetMATHCrossRef

37.

Tang, J. C., Cebrian, M., Giacobe, N. A., Kim, H.-W., Kim, T., & Wickert, D. B. (2011). Reflecting on the darpa red balloon challenge. Communications of the ACM, 54(4), 78–85.CrossRef

38.

Vojnovic, M. (2015). Contest theory. Cambridge: Cambridge University Press.CrossRef

39.

Wang, Z., & Xu, M. (2012). Learning and strategic sophistication in games: The case of penny auctions on the internet. Working paper.

40.

Yang, J., Adamic, L. A., & Ackerman, M. S. (2008). Crowdsourcing and knowledge sharing: strategic user behavior on taskcn. In Proceedings of the 9th ACM conference on electronic commerce, EC ’08 (pp. 246–255). New York: ACM.

41.

Young, H. P. (2004). Strategic learning and its limits. Oxford: Oxford University Press.CrossRef

Titel: Strategic behavior and learning in all-pay auctions: an empirical study using crowdsourced data
verfasst von: Yoram Bachrach
Ian A. Kash
Peter Key
Joel Oren
Publikationsdatum: 22.02.2019
Verlag: Springer US
Erschienen in: Autonomous Agents and Multi-Agent Systems / Ausgabe 1-2/2019
Print ISSN: 1387-2532
Elektronische ISSN: 1573-7454
DOI: https://doi.org/10.1007/s10458-019-09402-4

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Weitere Artikel der Ausgabe 1-2/2019

Towards an Internet of Agents model based on Linked Open Data approach

Systemic design of distributed multi-UAV cooperative decision-making for multi-target tracking

Multi-agent soft constraint aggregation via sequential voting: theoretical and experimental results

A probabilistic argumentation framework for reinforcement learning agents

Computing optimal coalition structures in polynomial time

A context-aware convention formation framework for large-scale networks

Premium Partner