![anylogic simulation examples anylogic simulation examples](https://i.ytimg.com/vi/cT86HApwCcg/maxresdefault.jpg)
This article is part of the theme issue ‘Modelling infectious disease outbreaks in humans, animals and plants: epidemic forecasting and control’.
![anylogic simulation examples anylogic simulation examples](https://www.anylogic.com/upload/iblock/8aa/8aab3b06f36e9f4adc213dc803d56371.jpg)
We further illustrate two approaches for translating the complex machine-readable policies into simple heuristics that can be evaluated by human decision-makers.
![anylogic simulation examples anylogic simulation examples](https://mosimtec.com/wp-content/uploads/2019/05/Examples-of-Agent-based-modeling.jpg)
We show that control based on the resulting context-dependent policies, which adapt interventions to the specific outbreak, result in smaller outbreaks than static policies.
![anylogic simulation examples anylogic simulation examples](https://www.anylogic.ru/upload/medialibrary/87a/87af00e8dc8cd1cccee57c5a11602321.jpg)
Here we illustrate the application of RL to the development of context-dependent outbreak response policies to minimize outbreaks of foot-and-mouth disease. RL could be a valuable tool to generate context-dependent policies for outbreak response, though translating the resulting policies into simple rules that can be read and interpreted by human decision-makers remains a challenge. Reinforcement learning (RL) and Monte Carlo control have been used to develop machine-readable context-dependent solutions for complex problems with many possible realizations ranging from video-games to the game of Go. Furthermore, there is no guarantee that the control actions that are optimal, on average, over all possible epidemics are also best for each possible epidemic. The number of all possible epidemics of a given infectious disease that could occur on a given landscape is large for systems of real-world complexity. This method can be easily mimicked to represent similar service industry models with similar decision points. This model acts as a guiding example that shows the ease of applying RL in AnyLogic models using the Pathmind Library. In this paper, we study the operations of an imaginary coffee shop with a focus on the barista's actions and show how the sequence of actions affects the overall performance of the coffee shop by using RL. However, the cost of adding more baristas increased the overall operational cost of the coffee shop. In Kadioglu (2017), a coffee shop simulation model concluded that increasing more baristas reduced the average service time. Coffee shop operations have been previously studied with a focus on optimizing employee availability, customer table placement, and reducing customer service time. A summary of different applications of RL can be found in Li (2017). In Olsen and Fraczkowski (2015), RL was used to study the coevolution of a predator-prey environment using an agent-based model to provide population dynamics and evolutionary insights in species. (2019), RL developed context-dependent dynamic response policies to minimize infectious disease outbreaks outperforming human generated static policies. (2005), a stochastic lot-scheduling problem (SELSP) was optimized using a dynamic RL policy to outperform various cyclic policies to meet production constraints and keep setup, inventory, and backorder costs low. Lately RL applications have spread across domains like supply chain, social, environmental and health sciences. 1 INTRODUCTION Reinforcement Learning (RL) as a simulation optimization technique has shown substantial results in the fields of game playing and robotics (Kaelbling et al. The trained policy outperforms rule-based functions in terms of customer service time and throughput. A coffee shop simulation is built to train a barista to make correct operational decisions and improve efficiency that directly affects customer service time.
Anylogic simulation examples software#
In this paper, we demonstrate the use of reinforcement learning in AnyLogic software models using Pathmind. Reinforcement Learning has recently gained a lot of exposure in the simulation industry.