Abstract
It is common in online markets for agents to learn from others' actions. Such observational learning can lead to herding or information cascades in which agents eventually "follow the crowd". Models for such cascades have been well studied for Bayes-rational agents faced with deciding between two possible actions-one "good"action and one "bad"action. In this paper, we consider the case when these agents instead have more than two actions, where again only one of these is good. We show that sequential observational learning in such settings has substantially different properties compared to the binary action case and further show than increasing the number of "bad"choices from 1 to 2, can improve the agents' learning.
| Original language | English (US) |
|---|---|
| Title of host publication | 2024 IEEE International Symposium on Information Theory, ISIT 2024 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 3302-3307 |
| Number of pages | 6 |
| ISBN (Electronic) | 9798350382846 |
| DOIs | |
| State | Published - 2024 |
| Event | 2024 IEEE International Symposium on Information Theory, ISIT 2024 - Athens, Greece Duration: Jul 7 2024 → Jul 12 2024 |
Publication series
| Name | IEEE International Symposium on Information Theory - Proceedings |
|---|---|
| ISSN (Print) | 2157-8095 |
Conference
| Conference | 2024 IEEE International Symposium on Information Theory, ISIT 2024 |
|---|---|
| Country/Territory | Greece |
| City | Athens |
| Period | 7/7/24 → 7/12/24 |
Funding
This work was supported in part by the NSF under grants CNS-1908807, ECCS-2030251 and ECCS-2216970.
ASJC Scopus subject areas
- Theoretical Computer Science
- Information Systems
- Modeling and Simulation
- Applied Mathematics