Chopra, Ayush, et al. "flame: A Framework for Learning in Agent-based ModEls." Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. 2024.

Abstract

Agent-based models (ABMs) are discrete simulators comprising agents that act and interact in a computational world. Despite wide applicability, infrastructure for ABMs has been fragmented and lacks a standard framework to integrate benefits of recent computing advances, especially in machine learning and automatic differentiation (autograd). To alleviate this gap we introduce flame: a framework to define, simulate and optimize differentiable agent-based models. First, flame introduces a domain-specific language that describes ABMs with stochastic dynamics across several domains and can be implemented using abstractions of autograd. Second, flame models can execute simulations on GPU, process millions of interactions per second and seamlessly scale from few hundred agents to million-size populations. Third, flame provides custom utilities to implement fully differentiable ABMs which can benefit from gradient-based learning and integrate with deep neural networks (DNNs), in several ways. Specifically, ABMs can now use supervised and reinforcement learning to calibrate simulation parameters, optimize agent actions and learn expressive interaction rules. Finally, flame is easily accessible with a simple Python API. We validate flame through multiple case studies that study tissue morphogenesis over bio-electric networks, infectious disease epidemiology over physical networks and opinion dynamics over social networks. We hope flame can ignite further innovation at the intersection of AI and ABMs.