Summary of Simulating the Economic Impact Of Rationality Through Reinforcement Learning and Agent-based Modelling, by Simone Brusatin et al.
Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modelling
by Simone Brusatin, Tommaso Padoan, Andrea Coletta, Domenico Delli Gatti, Aldo Glielmo
First submitted to arxiv on: 3 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Multiagent Systems (cs.MA); General Economics (econ.GN)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers propose a new approach to agent-based modeling (ABM) that combines simulation models with multi-agent reinforcement learning (RL) to create “fully rational” agents. These agents learn their behavior by interacting with the environment and maximizing a reward function. The authors introduce the Rational macro ABM (R-MABM) framework, which extends a well-known macroeconomic model from the economic literature. They show that replacing traditional bounded-rational agents in an ABM with RL agents trained to maximize profits leads to new insights into the impact of rationality on the economy. Specifically, they find that RL agents learn three distinct strategies for maximizing profits and segregate into different strategic groups when their policies are independent. The authors also demonstrate that a higher number of “rational” agents in an economy can improve macroeconomic outcomes at the cost of increased instability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to create agent-based models (ABMs) that makes them more realistic and useful for studying complex economic systems. Instead of using simple rules, the new model lets agents learn how to behave by interacting with each other and their environment. The authors show that this approach can help us understand better how people make decisions in markets and how this affects the overall economy. |
Keywords
» Artificial intelligence » Reinforcement learning
