Abstract
There are many settings in which agents learn from observing the actions of other agents. Bayesian observational learning models provide a framework for studying such situations and have been well-studied in settings where agents sequentially choose Bayes' optimal actions by learning from the actions of previous agents. Here, we consider such observational learning in a mean-field game setting, in which agents repeatedly choose actions over time to maximize an infinite horizon discounted pay-off. This pay-off depends on the underlying mean-field population state, which agents do not know and only have a prior common belief over it. At the end of each time-step, agents observe a common signal which is an imperfect observation of the mean-field action profile played in that time-step and use this to update their beliefs. We give a sequential decomposition of this game that enables one to characterize Markov perfect equilibria of the game. We then focus on a particular sub-class of these games which can be viewed as a mix of coordination/anti-coordination players. Using the sequential decomposition, we characterize the impact of varying the observation quality on the outcome of the game and show that this can exhibit non-monotonic behaviour, where in many instances, poorer observations lead to better expected total discounted pay-offs.
Original language | English (US) |
---|---|
Title of host publication | 2023 59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9798350328141 |
DOIs | |
State | Published - 2023 |
Event | 59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023 - Monticello, United States Duration: Sep 26 2023 → Sep 29 2023 |
Publication series
Name | 2023 59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023 |
---|
Conference
Conference | 59th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2023 |
---|---|
Country/Territory | United States |
City | Monticello |
Period | 9/26/23 → 9/29/23 |
Funding
This work was supported in part by the NSF under grants CNS-1908807 and ECCS-2216970.
ASJC Scopus subject areas
- Artificial Intelligence
- Computational Theory and Mathematics
- Computer Networks and Communications
- Computer Science Applications
- Computational Mathematics
- Control and Optimization