- Expectation formation
- Deep reinforcement learning algorithms and artificial intelligent techniques
Learning to make consumption-saving decisions in an adaptive environment: an AI approach. Current version.
Abstract: This exercise introduces AI algorithms to economic models highlighting how the two can be blended and produced innovative agents’ learning mechanism. In particular, this AI agent has limited or no information on the underlying economic structure and his own preference. It is able to learn in real time through constantly interacting with the environment and adjust its actions accordingly. I illustrate that the economic agent under deep reinforcement learning is adaptive to changes in the environment in real time. The AI agent’s learning characteristics, governed by parameters within the learning algorithms, can also be adjusted, which leads to sophisticated learning behaviours with welfare implications. The chosen economic structural can be generalised to other decision-making processes and economic models.
Selected Grants and Awards
- ESRC/ Rebuilding Macroeconomics Grant, 2019 (Co-investigator)
- Financial Economics: 3rd year BSc Economics module, Term 2 2019/20
- Intermediate Econometrics: 2nd year BSc Economics module, Term 2 2019/20
Deep Learning in a New Keynesian Model of Banking and Money Creation (July 2019 - July 2020)
Other partners: Mingli Chen, Andreas Joseph, Michael Kumhof, and Xinlei Pan.