In the on-line Explore and Exploit literature, central to Machine Learning, a central planner is faced with a set of alternatives, each yielding some unknown reward. The planner's goal is to learn the optimal alternative as soon as possible, via experimentation. A typical assumption in this model is that the planner has full control over the experiment design and implementation. When experiments are implemented by a society of self-motivated agents the planner can only recommend experimentation but has no power to enforce it. Kremer et al (JPE, 2014) introduce the first study of explore and exploit schemes that account for agents' incentives. In their model it is implicitly assumed that agents do not see nor communicate with each other. Their main result is a characterization of an optimal explore and exploit scheme. In this work we extend Kremer et al (JPE, 2014) by adding a layer of a social network according to which agents can observe each other. It turns out that when observability is factored in the scheme proposed by Kremer et al (JPE, 2014) is no longer incentive compatible. In our main result we provide a tight bound on how many other agents can each agent observe and still have an incentive-compatible algorithm and asymptotically optimal outcome. More technically, for a setting with N agents where the number of nodes with degree greater than N^alpha is bounded by N^beta and 2*alpha+beta < 1 we construct incentive-compatible asymptotically optimal mechanism. The bound 2*alpha+beta < 1 is shown to be tight.
[1]
Elchanan Mossel,et al.
Strategic Learning and the Topology of Social Networks
,
2012,
ArXiv.
[2]
Manuel Mueller-Frank,et al.
A general framework for rational learning in social networks
,
2011
.
[3]
A. Banerjee,et al.
A Simple Model of Herd Behavior
,
1992
.
[4]
Yishay Mansour,et al.
Bayesian Incentive-Compatible Bandit Exploration
,
2018
.
[5]
Gábor Lugosi,et al.
Prediction, learning, and games
,
2006
.
[6]
Noga Alon,et al.
Sequential voting with externalities: herding in social networks
,
2012,
EC '12.
[7]
S. Bikhchandani,et al.
You have printed the following article : A Theory of Fads , Fashion , Custom , and Cultural Change as Informational Cascades
,
2007
.
[8]
Yishay Mansour,et al.
Implementing the “Wisdom of the Crowd”
,
2013,
Journal of Political Economy.
[9]
Moshe Tennenholtz,et al.
Emergent Conventions in Multi-Agent Systems: Initial Experimental Results and Observations (Preliminary Report)
,
1992,
KR.
[10]
Nicolas Vieille,et al.
Informational externalities and emergence of consensus
,
2009,
Games Econ. Behav..
[11]
Ilan Lobel,et al.
BAYESIAN LEARNING IN SOCIAL NETWORKS
,
2008
.
[12]
R. Aumann.
Agreeing to disagree.
,
1976,
Nature cell biology.
[13]
James E. Kittock.
The Impact of Locality and Authority on Emergent Conventions: Initial Observations
,
1994,
AAAI.
[14]
Lones Smith,et al.
Pathological Outcomes of Observational Learning
,
2000
.