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

arXiv: https://arxiv.org/abs/2204.14076 · HTML: https://mlsanity.com/paper/2204.14076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 26 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [A Study on Overfitting in Deep Reinforcement Learning](https://mlsanity.com/paper/1804.06893/) (2018)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Generalization and Regularization in DQN](https://mlsanity.com/paper/1810.00123/) (2018)
- [Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1910.05396/) (2019)
- [Observational Overfitting in Reinforcement Learning](https://mlsanity.com/paper/1912.02975/) (2019)
- [Control of chaotic systems by Deep Reinforcement Learning](https://mlsanity.com/paper/1906.07672/) (2019)
- [Segregation Dynamics with Reinforcement Learning and Agent Based Modeling](https://mlsanity.com/paper/1909.08711/) (2019)
- [Multi-agent systems and decentralized artificial superintelligence](https://mlsanity.com/paper/1702.08529/) (2017)
- [Deep Reinforcement Learning for Online Control of Stochastic Partial Differential Equations](https://mlsanity.com/paper/2110.11265/) (2021)

## Abstract (arXiv)

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.