A Deterministic Protocol for Sequential Asymptotic Learning
- Creators
- Cheng, Yu
- Hann-Caruthers, Wade
- Tamuz, Omer
Abstract
In the classic herding model, agents receive private signals about an underlying binary state of nature, and act sequentially to choose one of two possible actions, after observing the actions of their predecessors. We investigate what types of behaviors lead to asymptotic learning, where agents will eventually converge to the right action in probability. It is known that for rational agents and bounded signals, there will not be asymptotic learning. Does it help if the agents can be cooperative rather than act selfishly? This is simple to achieve if the agents are allowed to use randomized protocols. In this paper, we provide the first deterministic protocol under which asymptotic learning occurs. In addition, our protocol has the advantage of being much simpler than previous protocols.
Additional Information
© 2018 IEEE. Part of this work was done while Yu Cheng was a student at the University of Southern California. Yu Cheng was supported in part by Shang-Hua Teng's Simons Investigator Award. Omer Tamuz was supported in part by grant #419427 from the Simons Foundation.Attached Files
Submitted - 1802.06871.pdf
Files
Name | Size | Download all |
---|---|---|
md5:9bfabde3bd5598073d5acac91620f0ee
|
100.2 kB | Preview Download |
Additional details
- Eprint ID
- 91194
- Resolver ID
- CaltechAUTHORS:20181126-153354872
- 419427
- Simons Foundation
- Created
-
2018-11-27Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field