Deep Reinforcement Learning in a Monetary Model
Release time：18 November 2025
Nov
21
|
Time & Date
|
15:30 pm
-
17:00 pm,
November
21,
2025
(Friday)
|
|
Venue
|
Room 904, Teaching Complex D Building
|
| TOPIC | Deep Reinforcement Learning in a Monetary Model |
| TIME&DATE | 03:30 pm-05:00 pm, November 21, 2025 (Friday) |
| Venue | Room 904, Teaching Complex D Building |
| Speaker |
Mingli Chen University of Warwick |
| Abstract | We propose deep reinforcement learning (DRL) as a general approach to modeling bounded rationality in dynamic stochastic general equilibrium (DSGE) frameworks. Agents are represented by deep artificial neural networks and learn to maximize their intertemporal objective functions by interacting with an a priori unknown environment. Applying this approach to a model from the adaptive learning literature, DRL agents can learn all equilibria, regardless of local stability properties. However, learning can be slow and may become unstable without the use of early stopping criteria. These findings have implications for both the interpretation of DRL agents and the use of DSGE models more broadly. |
| Biography | Mingli Chen is an Associate Professor of Economics in the Department of Economics at the University of Warwick, a Research Associate in CeMMAP, and a Turing Fellow at the Alan Turing Institute (the UK’s National Institute for Data Science and Artificial Intelligence). She received her PhD from Boston University and has held visiting positions at UC Berkeley, Stanford University, and the Federal Reserve Bank of Boston. Her research interests include Econometrics, Machine Learning, and AI in Economics. Her papers have been published in leading economics and statistics journals such as the Journal of Econometrics, the Journal of the Royal Statistical Society: Series B, and the Annals of Statistics. She won the LABOUR Prize at the Seventh Italian Congress of Econometrics and Empirical Economics, and received an Honorable Mention in the Arnold Zellner Thesis Award Competition by the Journal of Business and Economic Statistics in 2017. Starting in January 2024, she also serves as an Associate Editor of the Journal of Econometrics. |
