Reverse emulating agent-based models for policy simulation
This is an idea proposed in 2023 as a Cambrige Computer Science Part III or MPhil project, and has been completed by Pedro Sousa. It was supervised by Anil Madhavapeddy and Sadiq Jaffer.
Governments increasingly rely on simulation tools to inform policy design. Agent-based models (ABMs) simulate complex systems to study the emergent phenomena of individual behaviours and interactions in agent populations. However, these ABMs force an iterative, time-consuming, unmethodical parameter tuning of key policy "levers" (or input parameters) to steer the model towards the envisioned outcomes. To unlock a more natural workflow, this project investigates reverse emulation, a novel approach that streamlines policy design using probabilistic machine learning to predict parameter values that yield the desired policy outcomes.
Background reading
- J. Dyer, P. Cannon, J. D. Farmer, and S. M. Schmon, "Black-box bayesian inference for agent-based models", Journal of Economic Dynamics and Control, vol. 161, p. 104827, 2024.
- E. Frias-Martinez, G. Williamson, and V. Fr ́ıas-Mart ́ınez, "An agent-based model of epidemic spread using human mobility and social network information," pp. 57–64, 10 2011.
Links
- Publication to follow as it is currently being written up. The project was awarded the "2024 Highly Commended M.Phil Project" commendation from the Computer Science department.
See Also
This project was a followup to one in the previous year by Sharan Agrawal on Scalable agent-based models for optimized policy design.
ideasRelated News
Remote Sensing of Nature / Jan 2023
Measuring the world's forest carbon and biodiversity is made possible by remote sensing instruments, ranging from satellites in space (Landsat, Sentinel, GEDI) to ground-based sensors (ecoacoustics, camera traps, moisture sensors) that take regular samples and are processed into time-series metrics and actionable insights for conservation and human development. However, the algorithms for processing this data are challenging as the data is highly multimodal (multispectral, hyperspectral, synthetic aperture radar, or lidar), often sparsely sampled spatially, and not in a continuous time series. I work on various algorithms and software and hardware systems we are developing to improve the datasets we have about the surface of the earth. […904 words]
projectsScalable agent-based models for optimized policy design / Jan 2022
This is an idea proposed as a Cambrige Computer Science Part III or MPhil project, and has been completed by Sharan Agrawal. It was supervised by Anil Madhavapeddy and Srinivasan Keshav.
As the world faces twinned crises of climate change and biodiversity loss, the need for integrated policy approaches addressing both is paramount. To help address this, this project investigates a new agent-based model dubbed the VDSK-B. Using Dasgupta's review of the economics of biodiversity, it builds on the Dystopian Schumpeter meets Keynes (DSK) climate economics model to link together the climate, economy and biosphere. This is the first ABM proposed that integrates all 3 key elements.
The project also investigates how to scale such ABMs to be applicable for global policy design and scale to planetary-sized models. A new ABM framework called SalVO expresses agent updates as recursive applications of pure agent functions. This formalism differs from existing computational ABM models but is shown to be expressive enough to emulate a Turing complete language. SalVO is built on a JAX backend and designed to be scalable, vectorized, and optimizable. Employing hardware acceleration, tests showed it was more performant and more able to scale on a single machine than any existing ABM framework, such as FLAME (GPU). […252 words]