Gal Bahar
Moshe Tennenholtz
ABSTRACT
Technological evolution, so central to the progress of humanity in recent decades, is the process of constantly introducing new technologies to replace old ones. A new technology does not necessarily mean a better technology and so should not always be embraced. How can society learn which novelties present actual improvements over the existing technology? Whereas the quality of status-quo technology is well known, the new one is a pig in a poke. With sufficiently many individuals willing to explore the new technology society can learn whether it is indeed an improvement. However, self motivated agents, often, do not agree to explore. This is true, in particular, if agents observed some predecessors that were disappointed from the new technology. Inspired by the classical multi-armed bandit model we study a setting where agents arrive sequentially and must pull one of two arms in order to receive a reward - a risky arm (representing the new technology) and a safe arm (representing the existing one). A central planner must induce sufficiently many agents to experiment with the risky arm. The central planner observes the actions and rewards of all agents while the agents themselves have partial observation. For the setting where each agent observes his predecessor we provide the central planner with a recommendation algorithm that is (almost) incentive compatible and facilitates social learning.
Supplemental Material
- Daron Acemoglu, Munther A. Dahleh, Ilan Lobel, and Asuman Ozdaglar. Bayesian learning in social networks. Review of Economic Studies, 78:1--34, 2010.Google Scholar
- Mark Armstrong and Robert H. Porter. Handbook of Industrial Organization . 2007.Google Scholar
- Gal Bahar, Itai Arieli, Rann Smorodinsky, and Moshe Tennenholtz. Designing social networks for efficient learning. 2016. arXiv:1605.02489 {cs.GT}.Google Scholar
- Gal Bahar, Rann Smorodinsky, and Moshe Tennenholtz. Economic recommendation systems: One page abstract. In Proceedings of the 2016 ACM Conference on Economics and Computation, EC '16, pages 757--757, New York, NY, USA, 2016. ACM. Google ScholarDigital Library
- Banerjee. A simple model of herd behavior. The Quarterly Journal of Economics, 107:797--817, 1992.Google ScholarCross Ref
- S. Bikhchandani, D. Hirshleifer, and I. Welch. A theory of fads, fashion, custom and cultural change as information cascade. The Journal of Political Economy, 100:992--1026, 1992.Google ScholarCross Ref
- Sé bastien Bubeck and Nicolò Cesa-Bianchi. Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Foundations and Trends in Machine Learning, 5(1):1--122, 2012.Google ScholarCross Ref
- Y.K Che and J.O. Horner. Optimal design for social learning. Cowles Foundation Discussion Paper No. 2000, 2015.Google Scholar
- Peter I. Frazier, David Kempe, and Bangrui Chen. Incentivizing exploration by heterogeneous users. In Proceedings of Machine Learning Research vol 75, pages 1--21, 2018.Google Scholar
- Peter I. Frazier, David Kempe, Jon M. Kleinberg, and Robert Kleinberg. Incentivizing exploration. In ACM Conference on Economics and Computation, EC '14, Stanford, CA, USA, June 8--12, 2014, pages 5--22, 2014. Google ScholarDigital Library
- Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, and Zhiwei Steven Wu. Incentivizing exploration with unbiased histories. 2018. arXiv:1811.06026 {cs.GT}.Google Scholar
- Ilan Kremer, Yishay Mansour, and Motty Perry. Implementing the wisdom of the crowd. Journal of Political Economy, 122:988--1012, 2014.Google ScholarCross Ref
- Yishay Mansour, Aleksandrs Slivkins, and Vasilis Syrgkanis. Bayesian incentive-compatible bandit exploration. In ACM Conf. on Economics and Computation (EC), 2015.Google ScholarDigital Library
- Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis, and Zhiwei Steven Wu. Bayesian exploration: Incentivizing exploration in bayesian games. CoRR, abs/1602.07570, 2016.Google Scholar
- R. Myerson. Optimal coordination mechanisms in generalized principal--agent problemsn. Journal of Mathematical Economics, 10:67--81, 1982.Google ScholarCross Ref
- Joseph A Schumpeter. Capitalism, Socialism and Democracy. Harper and Brothers, 1942.Google Scholar
Index Terms
- Social Learning and the Innkeeper's Challenge
Recommendations
The recommendation mechanism for social learning environment
Although traditional e-learning has limitations of time and space, 'OpenCourseWare' further breaks through the limitations of classrooms and schools. It has given rise to a trend of online schools, with several famous universities even willing to ...
Social Reinforcement Learning in Game Playing
ICTAI '12: Proceedings of the 2012 IEEE 24th International Conference on Tools with Artificial Intelligence - Volume 01In this work we discuss Social Reinforcement Learning on self-trained agents. We simulate social learning by implementing a tournament on an existing board game that utilizes reinforcement learning for playing and learning. The socially trained agents ...
Social Learning
In recent years, social behavioral data have been exponentially expanding due to the tremendous success of various outlets on the social Web (aka Web 2.0) such as Facebook, Digg, Twitter, Wikipedia, and Delicious. As a result, there's a need for social ...
Comments