Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization

03/23/2021
by   Philipp Andelfinger, et al.
0

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 example of microscopic traffic models and an epidemics model, we study the fidelity and overhead of the differentiable models, as well as the convergence speed and solution quality achieved by gradient-based optimization compared to gradient-free methods. In traffic signal timing optimization problems with high input dimension, the gradient-based methods exhibit substantially superior performance. Finally, we demonstrate that the approach enables gradient-based training of neural network-controlled simulation entities embedded in the model logic.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/30/2018

optimParallel: an R Package Providing Parallel Versions of the Gradient-Based Optimization Methods of optim()

The R package optimParallel provides a parallel version of the gradient-...
research
10/04/2021

Differentiable Spline Approximations

The paradigm of differentiable programming has significantly enhanced th...
research
03/01/2020

Inverse design of photonic crystals through automatic differentiation

Gradient-based inverse design in photonics has already achieved remarkab...
research
08/31/2023

Branches of a Tree: Taking Derivatives of Programs with Discrete and Branching Randomness in High Energy Physics

We propose to apply several gradient estimation techniques to enable the...
research
07/20/2022

Differentiable Agent-based Epidemiology

Mechanistic simulators are an indispensable tool for epidemiology to exp...
research
09/26/2014

Gradient-based Taxis Algorithms for Network Robotics

Finding the physical location of a specific network node is a prototypic...
research
10/25/2022

Search for Concepts: Discovering Visual Concepts Using Direct Optimization

Finding an unsupervised decomposition of an image into individual object...

Please sign up or login with your details

Forgot password? Click here to reset