Affiliation:
1. University of Rostock, Rostock, Germany
Abstract
Simulation-based optimization using agent-based models is typically carried out under the assumption that the gradient describing the sensitivity of the simulation output to the input cannot be evaluated directly. To still apply gradient-based optimization methods, which efficiently steer the optimization towards a local optimum, gradient estimation methods can be employed. However, many simulation runs are needed to obtain accurate estimates if the input dimension is large. Automatic differentiation (AD) is a family of techniques to compute gradients of general programs directly. Here, we explore the use of AD in the context of time-driven agent-based simulations. By substituting common discrete model elements such as conditional branching with smooth approximations, we obtain gradient information across discontinuities in the model logic. On the examples of a synthetic grid-based model, an epidemics model, and a microscopic traffic model, we study the fidelity and overhead of the differentiable simulations as well as the convergence speed and solution quality achieved by gradient-based optimization compared with gradient-free methods. In traffic signal timing optimization problems with high input dimension, the gradient-based methods exhibit substantially superior performance. A further increase in optimization progress is achieved by combining gradient-free and gradient-based methods. We demonstrate that the approach enables gradient-based training of neural network-controlled simulation entities embedded in the model logic. Finally, we show that the performance overhead of differentiable agent-based simulations can be reduced substantially by exploiting sparsity in the model logic.
Funder
Deutsche Forschungsgemeinschaft
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Science Applications,Modeling and Simulation
Reference83 articles.
1. Mark S. Alber, Maria A. Kiskowski, James A. Glazier, and Yi Jiang. 2003. On cellular automaton approaches to modeling biological cells. In Mathematical Systems Theory in Biology, Communications, Computation, and Finance. Springer, 1–39.
2. Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization
3. Philipp Andelfinger, Jordan Ivanchev, David Eckhoff, Wentong Cai, and Alois Knoll. 2019. From effects to causes: Reversible simulation and reverse exploration of microscopic traffic models. In Proceedings of the 2019 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, ACM, Chicago, IL, USA, 173–184.
4. Fidelity and performance of state fast-forwarding in microscopic traffic simulations;Andelfinger Philipp;ACM Transactions on Modeling and Computer Simulation,2020
5. Accurate calibration of agent-based epidemiological models with neural network surrogates;Anirudh Rushil;arXiv preprint arXiv:2010.06558,2020
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献