An Economy of Neural Networks: Learning from Heterogeneous Experiences

2021/10/22 by Artem Kuriksha, Kuriksha, Artem · 2 citations
Computer Science · Economics, Econometrics and Finance · #Economic Policies and Impacts #Economic theories and models #FOS: Computer and information sciences #FOS: Economics and business #General Economics (econ.GN) #Monetary Policy and Economic Impact #Multiagent Systems (cs.MA) #cs.MA #econ.GN #q-fin.EC

paper · pdf · doi:10.48550/arxiv.2110.11582

47 pages

arxiv created 2021/10/22 · openalex publication_date 2021/10/22 · arxiv updated 2021/10/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper proposes a new way to model behavioral agents in dynamic macro-financial environments. Agents are described as neural networks and learn policies from idiosyncratic past experiences. I investigate the feedback between irrationality and past outcomes in an economy with heterogeneous shocks similar to Aiyagari (1994). In the model, the rational expectations assumption is seriously violated because learning of a decision rule for savings is unstable. Agents who fall into learning traps save either excessively or save nothing, which provides a candidate explanation for several empirical puzzles about wealth distribution. Neural network agents have a higher average MPC and exhibit excess sensitivity of consumption. Learning can negatively affect intergenerational mobility.

Citations

• Implications of rational inattention
• Decisions from Experience and the Effect of Rare Events in Risky Choice
• Continuous control with deep reinforcement learning
• Optimal Sticky Prices under Rational Inattention

Cited by

• Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
• EconGym: A Scalable AI Testbed with Diverse Economic Tasks

Related

• On the Equivalence of Neural and Production Networks
• Reinforcement Learning and Consumption-Savings Behavior
• Deep Reinforcement Learning in a Monetary Model
• A bright future for financial agent-based models
• Learning from zero: how to make consumption-saving decisions in a stochastic environment with an AI algorithm