Dynamic Noises of Multi-Agent Environments Can Improve Generalization: Agent-based Models meets Reinforcement Learning
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 26 Mar 2022.
Builds on
14 of 28 references.
References · 14
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
- 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
- 2018Quantifying Generalization in Reinforcement Learningcited by 345
- 2018A Study on Overfitting in Deep Reinforcement Learningcited by 170
- 2017Emergence of Locomotion Behaviours in Rich Environmentscited by 159
- 2018Assessing Generalization in Deep Reinforcement Learningcited by 132
- 2018Generalization and Regularization in DQNcited by 117
- 2019Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learningcited by 102
- 2019Observational Overfitting in Reinforcement Learningcited by 90
- 2019Control of chaotic systems by Deep Reinforcement Learningcited by 28
- 2019Segregation Dynamics with Reinforcement Learning and Agent Based Modelingcited by 9
Built on by
Not cited yet.