Deep Reinforcement Learning: Agents Mastering Economics in Fruit Market Environments

A recent paper explored how populations of deep reinforcement learning (deep RL) agents can learn microeconomic behaviors, such as production, consumption, and trading of goods. The artificial agents learn to make economically rational decisions about production, consumption, and prices, and react appropriately to supply and demand changes. The population converges to local prices that reflect the nearby abundance of resources, and some agents learn to transport goods between areas to “buy low and sell high”.

This work advances the broader multi-agent reinforcement learning research agenda by introducing new social challenges for agents to learn how to solve. The goal of multi-agent reinforcement learning research is to eventually produce agents that work across the full range and complexity of human social intelligence, so including domains like economics is crucial.

The subject matter of economics uses agent-based models to simulate how economies behave. Using a multi-agent simulated world, called Fruit Market, researchers have shown that agents can learn economic behaviors from scratch, including decisions about production, consumption, and prices. The agents must also navigate a physical environment, find resources, and trade with other agents.

In experiments, it was demonstrated that current deep RL agents can learn to trade, and their behaviors in response to supply and demand shifts align with microeconomic theory predictions. This has implications for economics research and highlights the recent progress in multi-agent RL and deep RL techniques. This paper fills the gap in AI research and provides a platform for further research in economics and AI.

As a path to artificial general intelligence (AGI), multi-agent reinforcement learning research should encompass all critical domains of social intelligence, including traditional economic phenomena such as trade, bargaining, specialisation, consumption, and production. This paper fills this gap and provides a platform for further research by including the Fruit Market environment in the next release of the Melting Pot suite of environments. AI and economics are becoming increasingly intertwined, and this research is a significant step in understanding how AI can learn and function in economic environments.

Source link

Stay in the Loop

Get the daily email from AI Headliner that makes reading the news actually enjoyable. Join our mailing list to stay in the loop to stay informed, for free.

Latest stories

You might also like...