Dynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning

2022/03/26 by Mohamed Akrout, Amal Feriani, Akrout, Mohamed +2
Economics, Econometrics and Finance · Mathematics · Medicine · #Artificial Intelligence (cs.AI) #COVID-19 epidemiological studies #Complex Systems and Time Series Analysis #FOS: Computer and information sciences #Machine Learning (cs.LG) #Mathematical and Theoretical Epidemiology and Ecology Models #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2204.14076

openalex publication_date 2022/03/26 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28

Abstract

We study the benefits of reinforcement learning (RL) environments based on agent-based models (ABM). While ABMs are known to offer microfoundational simulations at the cost of computational complexity, we empirically show in this work that their non-deterministic dynamics can improve the generalization of RL agents. To this end, we examine the control of an epidemic SIR environments based on either differential equations or ABMs. Numerical simulations demonstrate that the intrinsic noise in the ABM-based dynamics of the SIR model not only improve the average reward but also allow the RL agent to generalize on a wider ranges of epidemic parameters.

Related

• Reinforcement Learning Agents in Colonel Blotto
• An Agent-Centric Dynamical Systems Perspective on Multi-Agent Reinforcement Learning
• Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning
• Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
• Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamics