More Like this

1. Exploring the Viability of Agent-Based Modeling to Extend Qualitative Research: Comparison of Computational Platforms

   Splendido, S.; Berdanier, C.G.P. (January 2023, ASEE annual conference exposition)

   The purpose of this methods paper is to identify the opportunities and applications of agent-based modeling (ABM) methods to interpretative qualitative and educational research domains. The context we explore in this paper considers graduate engineering attrition, which has been a funded research focus of our group for ten years. In attrition research, as with all human research, it is impossible and unethical to imperil real graduate students by subjecting them to acute stressors that are known to contribute to attrition in order to “test” different combinations of factors on persistence and attrition. However, agent-based modeling (ABM) methods have been applied in other human decision-making contexts in which a computer applies researcher programmed logic to digital actors, invoking them to make digital decisions that mimic human decision making. From our research team’s ten years of research studying graduate socialization and attrition and informed from a host of theories that have been used in literature to investigate doctoral attrition, this paper compares the utility of two programming languages, Python and NetLogo, in conducting agent-based modeling to model graduate attrition as a platform. In this work we show that both platforms can be used to simulate attrition and persistence scenarios for thousands of digital agent-students simultaneously to produce results that agree with both with previous qualitative data and that agree with aggregate attrition and persistence statistics from literature. The two languages differ in their integrated development environments (IDE) with the methods of producing the models customizable to fit the needs of the study. Additionally, the size of the intended agent pool impacted the efficiency of the data collection. As computational methods can transform educational research, this work provides both a proof-of-concept and recommendations for other researchers considering employing these methods with these and similar platforms. Ultimately, while there are many programming languages that can perform agent-based modeling tasks, researchers are responsible for translating high quality, theory-driven, interpretive research into a computational model that can model human decision-making processes. 

   more » « less
2. Assisted Parameter and Behavior Calibration in Agent-based Models with DistributedOptimization

   A'Auria, Matteo; Scott, Eric O.; Lather, Rajdeep Singh; Hilty, Javier (December 2020, International Conference on Practical Applications of Agents and Multi-Agent Systems (PAAMS))

   Agent-based modeling (ABM) has many applications in the social sciences, biology, computer science, and robotics. One of the most important and challenging phases in agent-based model development is the calibration of model parameters and agent behaviors. Unfortunately, for many models this step is done by hand in an ad-hoc manner or is ignored entirely, due to the complexity inherent in ABM dynamics. In this paper we present a general-purpose, automated optimization system to assist the model developer in the calibration of ABM parameters and agent behaviors. This system combines two popular tools: the MASON agent-based modeling toolkit and the ECJ evolutionary optimization library. Our system distributes the model calibration task over very many processors and provides a wide range of stochastic optimization algorithms well suited to the calibration needs of agent-based models. 

   more » « less
3. Agent-based model construction using inverse reinforcement learning

   https://doi.org/http://doi.org/10.1109/WSC.2017.8247872  

   Lee, K.; Rucker, M.; Scherer, W.; Beling, P.; Gerber, M.; Kang, H. (January 2017, 2017 Winter Simulation Conference (WSC))

   Agent-based modeling (ABM) assumes that behavioral rules affecting an agent's states and actions are known. However, discovering these rules is often challenging and requires deep insight about an agent's behaviors. Inverse reinforcement learning (IRL) can complement ABM by providing a systematic way to find behavioral rules from data. IRL frames learning behavioral rules as a problem of recovering motivations from observed behavior and generating rules consistent with these motivations. In this paper, we propose a method to construct an agent-based model directly from data using IRL. We explain each step of the proposed method and describe challenges that may occur during implementation. Our experimental results show that the proposed method can extract rules and construct an agent-based model with rich but concise behavioral rules for agents while still maintaining aggregate-level properties. 

   more » « less
4. SMoRe ParS: A novel methodology for bridging modeling modalities and experimental data applied to 3D vascular tumor growth

   https://doi.org/10.3389/fmolb.2022.1056461  

   Jain, Harsh Vardhan; Norton, Kerri-Ann; Prado, Bernardo Bianco; Jackson, Trachette L (December 2022, Frontiers in Molecular Biosciences)

   Multiscale systems biology is having an increasingly powerful impact on our understanding of the interconnected molecular, cellular, and microenvironmental drivers of tumor growth and the effects of novel drugs and drug combinations for cancer therapy. Agent-based models (ABMs) that treat cells as autonomous decision-makers, each with their own intrinsic characteristics, are a natural platform for capturing intratumoral heterogeneity. Agent-based models are also useful for integrating the multiple time and spatial scales associated with vascular tumor growth and response to treatment. Despite all their benefits, the computational costs of solving agent-based models escalate and become prohibitive when simulating millions of cells, making parameter exploration and model parameterization from experimental data very challenging. Moreover, such data are typically limited, coarse-grained and may lack any spatial resolution, compounding these challenges. We address these issues by developing a first-of-its-kind method that leverages explicitly formulated surrogate models (SMs) to bridge the current computational divide between agent-based models and experimental data. In our approach, Surrogate Modeling for Reconstructing Parameter Surfaces (SMoRe ParS), we quantify the uncertainty in the relationship between agent-based model inputs and surrogate model parameters, and between surrogate model parameters and experimental data. In this way, surrogate model parameters serve as intermediaries between agent-based model input and data, making it possible to use them for calibration and uncertainty quantification of agent-based model parameters that map directly onto an experimental data set. We illustrate the functionality and novelty of Surrogate Modeling for Reconstructing Parameter Surfaces by applying it to an agent-based model of 3D vascular tumor growth, and experimental data in the form of tumor volume time-courses. Our method is broadly applicable to situations where preserving underlying mechanistic information is of interest, and where computational complexity and sparse, noisy calibration data hinder model parameterization. 

   more » « less
5. Distributed, Automated Calibration of Agent-based Model Parameters and Agent Behaviors

   D'Auria, Matteo; Scott, Eric O.; Lather, Rajdeep Singh; Hilty, Javier; Luke, Sean (July 2020, Autonomous Agents and Multiagent Systems (AAMAS))

   Agent-based models can present special challenges to model calibration due in part to their high parameter count, tunable agent behaviors, complex emergent macrophenomena, and potentially long runtimes. However, due to this difficulty, these models are most often calibrated by hand, or with hand-coded optimization tools customized per-problem if at all. As simulations increase in complexity, we will require general-purpose, distributed model calibration tools tailored for the needs of agent-based models. In this paper, we present the results of a system we have developed which combines two popular tools, the MASON agent-based modeling toolkit, and the ECJ evolutionary optimization library. This system distributes the model calibration task over many processors, provides many stochastic optimization algorithms well suited to the calibration needs of agent-based models, and offers the ability to optimize not just model parameters but agent behaviors. 

   more » « less