This ABM re-implements and extends the simulation model of peer review described in Squazzoni & Gandelli (Squazzoni & Gandelli, 2013 - doi:10.18564/jasss.2128) (hereafter: ‘SG’). The SG model was originally developed for NetLogo and is also available in CoMSES at this link.
The purpose of the original SG model was to explore how different author and reviewer strategies would impact the outcome of a journal peer review system on an array of dimensions including peer review efficacy, efficiency and equality. In SG, reviewer evaluation consists of a continuous variable in the range [0,1], and this evaluation scale is the same for all reviewers. Our present extension to the SG model allows to explore the consequences of two more realistic assumptions on reviewer evaluation: (1) that the evaluation scale is discrete (e.g. like in a Likert scale); (2) that there may be differences among their interpretation of the grades of the evaluation scale (i.e. that the grade language is heterogeneous).

Ecosystems are among the most complex structures studied. They comprise elements that seem both stable and contingent. The stability of these systems depends on interactions among their evolutionary history, including the accidents of organisms moving through the landscape and microhabitats of the earth, and the biotic and abiotic conditions in which they occur. When ecosystems are stable, how is that achieved? Here we look at ecosystem stability through a computer simulation model that suggests that it may depend on what constrains the system and how those constraints are structured. Specifically, if the constraints found in an ecological community form a closed loop, that allows particular kinds of feedback may give structure to the ecosystem processes for a period of time. In this simulation model, we look at how evolutionary forces act in such a way these closed constraint loops may form. This may explain some kinds of ecosystem stability. This work will also be valuable to ecological theorists in understanding general ideas of stability in such systems.

The purpose of this model is to explore the dynamics of residency and eviction for households renting in the greater Phoenix (Arizona) metropolitan area. The model uses a representative population of renters modified from American Community Survey (ACS) data that includes demographic, housing and economic information. Each month, households pay their subsistence, rental and utility bills. If a household is unable to pay their monthly rent or utility bill they apply for financial assistance. This model provides a platform to understand the impact of various economic shock upon households. Also, the model includes conditions that occurred as a result of the Covid-19 pandemic which allows for the study of eviction mitigation strategies that were employed, such as the eviction moratorium and stimulus payments. The model allows us to make preliminary predictions concerning the number of households that may be evicted once the moratorium on evictions ends and the long-term effects on the number of evicted households in the greater Phoenix area going forward.

The HERB model simulates the retrofit behavior of homeowners in a neighborhood. The model initially parameterizes a neighborhood and households with technical factors such as energy standard, the availability of subsidies, and neighbors’ retrofit activity. Then, these factors are translated into psychological variables such as perceived comfort gain, worry about affording the retrofit, and perceiving the current energy standard of the home as wasteful. These psychological variables moderate the transition between four different stages of deciding to retrofit, as suggested by a behavioral model specific to household energy retrofitting identified based on a large population survey in Norway. The transition between all stages eventually leads to retrofitting, which affects both the household’s technical factors and friends and neighbors, bringing the model “full circle”. The model assumes that the energy standard of the buildings deteriorates over time, forcing households to retrofit regularly to maintain a certain energy standard.

Because experiment datafiles are about 15GB, they are available at https://doi.org/10.18710/XOSAMD

Cooperation is essential for all domains of life. Yet, ironically, it is intrinsically vulnerable to exploitation by cheats. Hence, an explanatory necessity spurs many evolutionary biologists to search for mechanisms that could support cooperation. In general, cooperation can emerge and be maintained when cooperators are sufficiently interacting with themselves. This communication provides a kind of assortment and reciprocity. The most crucial and common mechanisms to achieve that task are kin selection, spatial structure, and enforcement (punishment). Here, we used agent-based simulation models to investigate these pivotal mechanisms against conditional defector strategies. We concluded that the latter could easily violate the former and take over the population. This surprising outcome may urge us to rethink the evolution of cooperation, as it illustrates that maintaining cooperation may be more difficult than previously thought. Moreover, empirical applications may support these theoretical findings, such as invading the cooperator population of pathogens by genetically engineered conditional defectors, which could be a potential therapy for many incurable diseases.

The model combines agent-based modelling and microeconomic approach to simulate the decision behaviour of land developers and how this impacts on the spatio-temporal processes of urban expansion.

A System Dynamics Model to anticipate insurgent movements and policy design to handle them .

This model implements a classic scenario used in Reinforcement Learning problem, the “Cliff Walking Problem”. Consider the gridworld shown below (SUTTON; BARTO, 2018). This is a standard undiscounted, episodic task, with start and goal states, and the usual actions causing movement up, down, right, and left. Reward is -1 on all transitions except those into the region marked “The Cliff.” Stepping into this region incurs a reward of -100 and sends the agent instantly back to the start (SUTTON; BARTO, 2018).

The problem is solved in this model using the Q-Learning algorithm. The algorithm is implemented with the support of the NetLogo Q-Learning Extension

IOP 2.1.2 is an agent-based simulation model designed to explore the relations between (1) employees, (2) tasks and (3) resources in an organizational setting. By comparing alternative cognitive strategies in the use of resources, employees face increasingly demanding waves of tasks that derive by challenges the organization face to adapt to a turbulent environment. The assumption tested by this model is that a successful organizational adaptation, called plastic, is necessarily tied to how employees handle pressure coming from existing and new tasks. By comparing alternative cognitive strategies, connected to ‘docility’ (Simon, 1993; Secchi, 2011) and ‘extended’ cognition (Clark, 2003, Secchi & Cowley, 2018), IOP 2.1.2 is an attempt to indicate which strategy is most suitable and under which scenario.

This model was developed to test the usability of evolutionary computing and reinforcement learning by extending a well known agent-based model. Sugarscape (Epstein & Axtell, 1996) has been used to demonstrate migration, trade, wealth inequality, disease processes, sex, culture, and conflict. It is on conflict that this model is focused to demonstrate how machine learning methodologies could be applied.

The code is based on the Sugarscape 2 Constant Growback model, availble in the NetLogo models library. New code was added into the existing model while removing code that was not needed and modifying existing code to support the changes. Support for the original movement rule was retained while evolutionary computing, Q-Learning, and SARSA Learning were added.