TaxAI: A Dynamic Economic Simulator and Benchmark for Multi-Agent Reinforcement Learning
Qirui Mi, Siyu Xia, Yan Song, Haifeng Zhang, Shenghao Zhu, Jun Wang

TL;DR
TaxAI is a large-scale, realistic multi-agent reinforcement learning environment simulating economic interactions among households, government, firms, and intermediaries, enabling better policy testing and development.
Contribution
The paper introduces TaxAI, a scalable, realistic MARL-based economic simulator based on the Bewley-Aiyagari model, and benchmarks its effectiveness against traditional methods.
Findings
MARL outperforms traditional economic methods in the TaxAI environment.
TaxAI can simulate interactions with up to 10,000 households.
The simulator demonstrates superior scalability and realism for policy analysis.
Abstract
Taxation and government spending are crucial tools for governments to promote economic growth and maintain social equity. However, the difficulty in accurately predicting the dynamic strategies of diverse self-interested households presents a challenge for governments to implement effective tax policies. Given its proficiency in modeling other agents in partially observable environments and adaptively learning to find optimal policies, Multi-Agent Reinforcement Learning (MARL) is highly suitable for solving dynamic games between the government and numerous households. Although MARL shows more potential than traditional methods such as the genetic algorithm and dynamic programming, there is a lack of large-scale multi-agent reinforcement learning economic simulators. Therefore, we propose a MARL environment, named \textbf{TaxAI}, for dynamic games involving households, government,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEconomic theories and models · Complex Systems and Time Series Analysis
