mlsanityData to 7 Oct 2026

Interventionally Consistent Surrogates for Agent-based Simulators

arXiv 2312.11158 ↗First posted 18 Dec 2023cs.MA cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Agent-based simulators provide granular representations of complex intelligent systems by directly modelling the interactions of the system's constituent agents. Their high-fidelity nature enables hyper-local policy evaluation and testing of what-if scenarios, but is associated with large computational costs that inhibits their widespread use. Surrogate models can address these computational limitations, but they must behave consistently with the agent-based model under policy interventions of interest. In this paper, we capitalise on recent developments on causal abstractions to develop a framework for learning interventionally consistent surrogate models for agent-based simulators. Our proposed approach facilitates rapid experimentation with policy interventions in complex systems, while inducing surrogates to behave consistently with high probability with respect to the agent-based simulator across interventions of interest. We demonstrate with empirical studies that observationally trained surrogates can misjudge the effect of interventions and misguide policymakers towards suboptimal policies, while surrogates trained for interventional consistency with our proposed method closely mimic the behaviour of an agent-based model under interventions of interest.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 13 of its 37 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

13 of 37 references.

References · 13

  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2020Universal Differential Equations for Scientific Machine Learningcited by 345
  3. 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
  4. 2017Causal Consistency of Structural Equation Modelscited by 114
  5. 2018Abstracting Causal Modelscited by 104
  6. 2019Approximate Causal Abstractioncited by 62
  7. 2021Compositional Abstraction Error and a Category of Causal Modelscited by 32
  8. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 21
  9. 2022Black-box Bayesian inference for economic agent-based modelscited by 13
  10. 2020Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogatescited by 9
  11. 2021Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)cited by 9
  12. 2022Calibrating Agent-based Models to Microdata with Graph Neural Networkscited by 7
1 more
  1. 2023Quantifying Consistency and Information Loss for Causal Abstraction Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2025Multifidelity Simulation-based Inference for Computationally Expensive Simulatorscited by 9
  2. 2024Aligning Graphical and Functional Causal Abstractionscited by 6
  3. 2026Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world modelscited by 6
  4. 2024Causally Abstracted Multi-armed Banditscited by 5
  5. 2024Bayesian calibration of stochastic agent based model via random forestcited by 4
  6. 2025Combining Causal Models for More Accurate Abstractions of Neural Networkscited by 4