AI4ABM Workshop at the International Conference on Machine Learning (ICML) 2022

Key dates

  • Paper submission deadline: 26 May 2022 Friday, May 27th 2022 Anywhere on Earth (1 pm GMT on Saturday, May 28th)
  • Paper acceptance notification deadline: 13 June 2022
  • Recording submission deadline: 1 July 2022
  • Workshop date: 23 July 2022 (CONFIRMED) - Room 318 - 320 T380

Mentorship Program

AI4ABM is hosting a mentorship program in which we pair senior researchers with junior mentees who are wishing to submit a paper to the workshop. Senior researcher volunteers will be matched with junior researchers (< 3 years of Ph.D.-level research experience) at a rolling basis - so please apply ASAP!
To sign up as either mentor or mentee please use the following forms:

Mentee sign-up link.
Mentor sign-up link.

Both mentees and senior mentors are free to arrange their mentorship relationship at their own discretion, however, we do suggest mentors and mentees should strive to entertain weekly update calls until the workshop submission deadline. In case there is a shortage of mentors, mentees from underprivileged background will be given preference.

Aims and Focus

Many of the world’s most pressing issues, such as climate change, pandemics, financial market stability and fake news, are emergent phenomena that result from the interaction between a large number of strategic or learning agents. Understanding these systems is thus a crucial frontier for scientific and technology development that has the potential to permanently improve the safety and living standards of humanity. Agent-Based Modelling (ABM) (also known as individual-based modelling) is an approach toward creating simulations of these types of complex systems by explicitly modelling the actions and interactions of the individual agents contained within. This approach, unlike equation-based modelling techniques, has been shown to enable the study of complex heterogeneous systems, including in non-equilibrium settings. ABMs have recently seen increasing interest across various disciplines, ranging from economics(Arthur, 1994; Buchanan, 2009; Lamperti et al., 2019) and epidemiology (Ferguson et al., 2005; Ferris et al., 2015) to cybersecurity (Thompson & Morris-King, 2018), social sciences (Conte & Paolucci, 2014; Gilbert & Doran, 1994; Sert et al., 2020), and climate policy(Gerst et al., 2013), not least through their use in the COVID19-pandemic (Wang et al., 2021; Truszkowska et al., 2021; Hinch et al., 2021; Kerr et al., 2021) . However, current methodologies for calibrating and validating ABMs to real-world data generally rely on low-dimensional summary statistics crafted by human domain experts (Andrianakis et al., 2015; Platt, 2019). In addition, current ABMs are still very much based on heuristic approaches, e.g. relying on hand-coded behaviours for individual agents and environment dynamics.

The field has thus far taken little advantage of the recent progress in AI, which has the potential to offer exciting new approaches to learning, calibrating, validation, analysing and accelerating such models, including deep multi-agent learning and simulation-based inference. This interdisciplinary workshop is meant to bring together practitioners and theorists to boost ABM method development in AI, and stimulate novel applications across disciplinary boundaries. Based on attendance and interest in our weekly new AI4ABM community meetings at Oxford (and remote), it has become clear that there is a need for an interdisciplinary space to bring AI researchers and ABM practitioners together to stimulate research on the intersection of both. A workshop at ICML is a perfect venue for this, since the ICML community has all of the required expertise in Machine Learning and also has shown previous interest in expanding to new application domains (cf this workshop).

Our inaugural workshop will be organised along two axes. First, we seek to provide a venue where ABM researchers from a variety of domains can introduce AI researchers to their respective domain problems, ranging from economics (Zheng et al., 2021; Curry et al., 2022; Radovic et al., 2021), finance (Castro et al., 2020), epidemiology (Reiker et al., 2021; Reiker et al., 2021; Alsdurf et al., 2020; Gram-Hansen et al., 2019), biology (Girvan et al., 2002; Kolic et al., 2021), to the social and political sciences (Girvan & Newman, 2002; Aymanns et al., 2017), and physics (Baydin et al., 2019). To this end, we are inviting a number of high-profile speakers across various application domains, including network and complex systems scientists who might not ordinarily attend ICML.

Second, we seek to stimulate research into AI methods that can scale to large-scale agent-based models with the potential to redefine our capabilities of creating, calibrating, and validating such models. These methods can be broadly divided into simulation-based inference (Cranmer et al., 2020; Lavin et al., 2021), which is an umbrella term for a large variety of likelihood-based and likelihood-free scalable probabilistic inference methods ranging from emulation techniques to probabilistic programming, and multi-agent learning (Foerster, 2018; Sutton & Barto, 1998), which encompasses fields such as deep multi-agent reinforcement learning, genetic algorithms, as well as inverse learning. Other relevant AI methods whose development for agent-based modelling we seek to stimulate include causal inference and discovery, program synthesis, and the development of domain-specific languages and tools that allow for tight integration of ABMs and AI approaches.

Call for Papers

For our international Call for Papers, please see this page.


  1. Arthur, W. B. (1994). Inductive Reasoning and Bounded Rationality. The American Economic Review, 84(2), 406–411.
    Publisher: American Economic Association
  2. Buchanan, M. (2009). Economics: Meltdown modelling. Nature, 460(7256), 680–682.
    Number: 7256 Publisher: Nature Publishing Group
  3. Lamperti, F., Mandel, A., Napoletano, M., Sapio, A., Roventini, A., Balint, T., & Khorenzhenko, I. (2019). Towards agent-based integrated assessment models: examples, challenges, and future developments. Regional Environmental Change, 19(3), 747–762.
  4. Ferguson, N. M., Cummings, D. A. T., Cauchemez, S., Fraser, C., Riley, S., Meeyai, A., Iamsirithaworn, S., & Burke, D. S. (2005). Strategies for containing an emerging influenza pandemic in Southeast Asia. Nature, 437(7056), 209–214.
    Number: 7056 Publisher: Nature Publishing Group
  5. Ferris, C., Raybaud, B., & Madey, G. (2015). OpenMalaria and EMOD: a case study on model alignment. Proceedings of the Conference on Summer Computer Simulation, 1–9.
  6. Thompson, B., & Morris-King, J. (2018). An agent-based modeling framework for cybersecurity in mobile tactical networks. The Journal of Defense Modeling and Simulation, 15(2), 205–218.
    Publisher: SAGE Publications
  7. Conte, R., & Paolucci, M. (2014). On agent-based modeling and computational social science. Frontiers in Psychology, 5.
  8. Gilbert, N., & Doran, J. (1994). Simulating Societies: Computer Simulation of Social Phenomena (N. Gilbert & J. Doran, Eds.). Routledge.
  9. Sert, E., Bar-Yam, Y., & Morales, A. J. (2020). Segregation dynamics with reinforcement learning and agent based modeling. Scientific Reports, 10(1), 11771.
    Number: 1 Publisher: Nature Publishing Group
  10. Gerst, M. D., Wang, P., Roventini, A., Fagiolo, G., Dosi, G., Howarth, R. B., & Borsuk, M. E. (2013). Agent-based modeling of climate policy: An introduction to the ENGAGE multi-level model framework. Environmental Modelling & Software, 44, 62–75.
  11. Wang, Y., Xiong, H., Liu, S., Jung, A., Stone, T., & Chukoskie, L. (2021). Simulation Agent-Based Model to Demonstrate the Transmission of COVID-19 and Effectiveness of Different Public Health Strategies. Frontiers in Computer Science, 3.
  12. Truszkowska, A., Behring, B., Hasanyan, J., Zino, L., Butail, S., Caroppo, E., Jiang, Z.-P., Rizzo, A., & Porfiri, M. (2021). High-Resolution Agent-Based Modeling of COVID-19 Spreading in a Small Town. Advanced Theory and Simulations, 4(3), 2000277.
  13. Hinch, R., Probert, W. J. M., Nurtay, A., Kendall, M., Wymant, C., Hall, M., Lythgoe, K., Cruz, A. B., Zhao, L., Stewart, A., Ferretti, L., Montero, D., Warren, J., Mather, N., Abueg, M., Wu, N., Legat, O., Bentley, K., Mead, T., … Fraser, C. (2021). OpenABM-Covid19—An agent-based model for non-pharmaceutical interventions against COVID-19 including contact tracing. PLOS Computational Biology, 17(7), e1009146.
    Publisher: Public Library of Science
  14. Kerr, C. C., Stuart, R. M., Mistry, D., Abeysuriya, R. G., Rosenfeld, K., Hart, G. R., Núñez, R. C., Cohen, J. A., Selvaraj, P., Hagedorn, B., George, L., Jastrzębski, M., Izzo, A. S., Fowler, G., Palmer, A., Delport, D., Scott, N., Kelly, S. L., Bennette, C. S., … Klein, D. J. (2021). Covasim: An agent-based model of COVID-19 dynamics and interventions. PLOS Computational Biology, 17(7), e1009149.
    Publisher: Public Library of Science
  15. Andrianakis, I., Vernon, I. R., McCreesh, N., McKinley, T. J., Oakley, J. E., Nsubuga, R. N., Goldstein, M., & White, R. G. (2015). Bayesian History Matching of Complex Infectious Disease Models Using Emulation: A Tutorial and a Case Study on HIV in Uganda. PLOS Computational Biology, 11(1), e1003968.
    Publisher: Public Library of Science
  16. Platt, D. (2019). A Comparison of Economic Agent-Based Model Calibration Methods. ArXiv:1902.05938 [Econ, q-Fin].
    arXiv: 1902.05938
  17. Zheng, S., Trott, A., Srinivasa, S., Parkes, D. C., & Socher, R. (2021). The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning. ArXiv:2108.02755 [Cs, Econ, q-Fin].
    arXiv: 2108.02755
  18. Curry, M., Trott, A., Phade, S., Bai, Y., & Zheng, S. (2022). Finding General Equilibria in Many-Agent Economic Simulations Using Deep Reinforcement Learning. ArXiv:2201.01163 [Cs, Econ, q-Fin].
    arXiv: 2201.01163
  19. Radovic, D., Kruitwagen, L., Schroeder de Witt, C., Caldecott, B., Tomlinson, S., & Workman, M. (2021). Revealing Robust Oil and Gas Company Macro-Strategies Using Deep Multi-Agent Reinforcement Learning (SSRN Scholarly Paper ID 3933996; Number ID 3933996). Social Science Research Network.
  20. Castro, P. S., Desai, A., Du, H., Garratt, R., & Rivadeneyra, F. (2020). Estimating Policy Functions in Payment Systems using Reinforcement Learning (SSRN Scholarly Paper ID 3743017; Number ID 3743017). Social Science Research Network.
  21. Reiker, T., Golumbeanu, M., Shattock, A., Burgert, L., Smith, T. A., Filippi, S., Cameron, E., & Penny, M. A. (2021). Machine learning approaches to calibrate individual-based infectious disease models (p. 2021.01.27.21250484). medRxiv.
    Type: article
  22. Reiker, T., Golumbeanu, M., Shattock, A., Burgert, L., Smith, T. A., Filippi, S., Cameron, E., & Penny, M. A. (2021). Emulator-based Bayesian optimization for efficient multi-objective calibration of an individual-based model of malaria. Nature Communications, 12(1), 7212.
    Number: 1 Publisher: Nature Publishing Group
  23. Alsdurf, H., Belliveau, E., Bengio, Y., Deleu, T., Gupta, P., Ippolito, D., Janda, R., Jarvie, M., Kolody, T., Krastev, S., Maharaj, T., Obryk, R., Pilat, D., Pisano, V., Prud’homme, B., Qu, M., Rahaman, N., Rish, I., Rousseau, J.-F., … Yu, Y. W. (2020). COVI White Paper. ArXiv:2005.08502 [Cs].
    arXiv: 2005.08502
  24. Gram-Hansen, B., de Witt, C. S., Rainforth, T., Torr, P. H. S., Teh, Y. W., & Baydin, A. G. (2019). Hijacking Malaria Simulators with Probabilistic Programming. ArXiv:1905.12432 [Cs, Stat].
    arXiv: 1905.12432
  25. Girvan, M., Callaway, D. S., Newman, M. E. J., & Strogatz, S. H. (2002). Simple model of epidemics with pathogen mutation. Physical Review E, 65(3), 031915.
    Publisher: American Physical Society
  26. Kolic, B., Sabuco, J., & Farmer, J. D. (2021). Estimating initial conditions for dynamical systems with incomplete information. ArXiv:2109.06825 [Math].
    arXiv: 2109.06825
  27. Girvan, M., & Newman, M. E. J. (2002). Community structure in social and biological networks. Proceedings of the National Academy of Sciences, 99(12), 7821–7826.
    Publisher: National Academy of Sciences Section: Physical Sciences
  28. Aymanns, C., Foerster, J., & Georg, C.-P. (2017). Fake News in Social Networks. ArXiv:1708.06233 [Physics, q-Fin].
    arXiv: 1708.06233
  29. Baydin, A. G., Shao, L., Bhimji, W., Heinrich, L., Meadows, L., Liu, J., Munk, A., Naderiparizi, S., Gram-Hansen, B., Louppe, G., Ma, M., Zhao, X., Torr, P., Lee, V., Cranmer, K., Prabhat, & Wood, F. (2019). Etalumis: bringing probabilistic programming to scientific simulators at scale. Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 1–24.
  30. Cranmer, K., Brehmer, J., & Louppe, G. (2020). The frontier of simulation-based inference. Proceedings of the National Academy of Sciences, 117(48), 30055–30062.
    Publisher: National Academy of Sciences Section: Colloquium Paper
  31. Lavin, A., Zenil, H., Paige, B., Krakauer, D., Gottschlich, J., Mattson, T., Anandkumar, A., Choudry, S., Rocki, K., Baydin, A. G., Prunkl, C., Paige, B., Isayev, O., Peterson, E., McMahon, P. L., Macke, J., Cranmer, K., Zhang, J., Wainwright, H., … Pfeffer, A. (2021). Simulation Intelligence: Towards a New Generation of Scientific Methods. ArXiv:2112.03235 [Cs].
    arXiv: 2112.03235
  32. Foerster, J. N. (2018). Deep multi-agent reinforcement learning [Http://, University of Oxford].
  33. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction (Vol. 1, Number 1). MIT press Cambridge.