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

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

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.

This model simulates networking mechanisms of an empirical social network. It correlates event determinants with place-based geography and social capital production.

In the consumer advice network, users with connections can interact with each other, and the network topology will change during the opinion interaction. When the opinion distance from i to j is greater than the confidence threshold, the two consumers cannot exchange opinions, and the link between them will disconnect with probability DE. Then, a link from node i to node k is established with probability CE and node i learning opinion from node k.

This project is based on a Jupyter Notebook that describes the stepwise implementation of the EWA model in bi-matrix ( 2×2 ) strategic-form games for the simulation of economic learning processes. The output is a dataset with the simulated values of Attractions, Experience, selected strategies, and payoffs gained for the desired number of rounds and periods. The notebook also includes exploratory data analysis over the simulated output based on equilibrium, strategy frequencies, and payoffs.

The present model was created and used for the study titled ``Agent-Based Insight into Eco-Choices: Simulating the Fast Fashion Shift.” The model is implemented in the multi-agent programmable environment NetLogo 6.3.0. The model is designed to simulate the behavior and decision-making processes of individuals (agents) in a social network. It focuses on how agents interact with their peers, social media, and government campaigns, specifically regarding their likelihood to purchase fast fashion.

A group of agents share a resource and agents will become sufficiently motivated to adopt a rule to constraint their freedom if they experience resource scarcity and developed mutual trust relationships.

Exploring how learning and social-ecological networks influence management choice set and their ability to increase the likelihood of species coexistence (i.e. biodiversity) on a fragmented landscape controlled by different managers.

Decision-makers often have to act before critical times to avoid the collapse of ecosystems using knowledge \textcolor{red}{that can be incomplete or biased}. Adaptive management may help managers tackle such issues. However, because the knowledge infrastructure required for adaptive management may be mobilized in several ways, we study the quality and the quantity of knowledge provided by this knowledge infrastructure. In order to analyze the influence of mobilized knowledge, we study how the following typology of knowledge and its use may impact the safe operating space of exploited ecosystems: 1) knowledge of the past based on a time series distorted by measurement errors; 2) knowledge of the current systems’ dynamics based on the representativeness of the decision-makers’ mental models of the exploited ecosystem; 3) knowledge of future events based on decision-makers’ likelihood estimates of extreme events based on modeling infrastructure (models and experts to interpret them) they have at their disposal. We consider different adaptive management strategies of a general regulated exploited ecosystem model and we characterize the robustness of these strategies to biased knowledge. Our results show that even with significant mobilized knowledge and optimal strategies, imperfect knowledge may still shrink the safe operating space of the system leading to the collapse of the system. However, and perhaps more interestingly, we also show that in some cases imperfect knowledge may unexpectedly increase the safe operating space by suggesting cautious strategies.
The code enables to calculate the safe operating spaces of different managers in the case of biased and unbiased knowledge.