An Economy of Neural Networks: Learning from Heterogeneous Experiences

  title={An Economy of Neural Networks: Learning from Heterogeneous Experiences},
  author={A. A. Kuriksha},
  • A. Kuriksha
  • Published 22 October 2021
  • Economics, Computer Science
  • ArXiv
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… 


A model of learning and emulation with artificial adaptive agents
We study adaptive learning behavior in a sequence of n-period endowment overlapping generations economies with fiat currency, where n refers to the number of periods in agents' lifetimes. Agents
Economic Agents as Imperfect Problem Solvers
We develop a tractable model of limited cognitive perception of the optimal policy function, with agents using costly reasoning effort to update beliefs about this optimal mapping of economic states
Financial Frictions and the Wealth Distribution
This paper investigates how, in a heterogeneous agents model with financial frictions, idiosyncratic individual shocks interact with exogenous aggregate shocks to generate time-varying levels of
Reinforcement Learning and Savings Behavior
We show that individual investors over-extrapolate from their personal experience when making savings decisions. Investors who experience particularly rewarding outcomes from saving in their 401(k)-a
Money as a medium of exchange in an economy with artificially intelligent agents
Abstract We study the exchange economies of Kiyotaki and Wright (1989) in which agents must use a commodity or fiat money as a medium of exchange if trade is to occur. Our agents are artificially
Deep Reinforcement Learning in a Monetary Model
We propose using deep reinforcement learning to solve dynamic stochastic general equilibrium models. Agents are represented by deep artificial neural networks and learn to solve their dynamic
Behavioral Macroeconomics Via Sparse Dynamic Programming
This paper proposes a tractable way to model boundedly rational dynamic programming. The agent uses an endogenously simplified, or "sparse," model of the world and the consequences of his actions and
Learning to make consumption-saving decisions in a changing environment: an AI approach
This exercise offers an innovative learning mechanism to model economic agent’s decision-making process using a deep reinforcement learning algorithm. In particular, this AI agent has limited or no
Asset Pricing with Fading Memory
Building on evidence that lifetime experiences shape individuals' macroeconomic expectations, we study asset prices in an economy in which a representative agent learns with fading memory about
Monetary Policy, Bounded Rationality, and Incomplete Markets
This paper extends the benchmark New-Keynesian model by introducing two frictions: (1) agent heterogeneity with incomplete markets, uninsurable idiosyncratic risk, and occasionally binding borrowing