Dynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning
This work addresses generalization challenges in reinforcement learning for epidemic control, offering a domain-specific improvement.
The paper tackled the problem of improving reinforcement learning agent generalization by using agent-based models (ABMs) for environment simulation, showing that ABM-based SIR epidemic environments with intrinsic noise increased average reward and allowed agents to generalize across a wider range of epidemic parameters.
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.