Matching Items (4)
Filtering by

Clear all filters

133880-Thumbnail Image.png
Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form

In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
147947-Thumbnail Image.png
Description

University Devils is a Founders Lab Thesis group looking to find a way for post-secondary institutions to increase the number of and diversity of incoming applications through the utilization of gaming and gaming approaches in the recruitment process while staying low-cost. This propelling question guided the group through their work.

University Devils is a Founders Lab Thesis group looking to find a way for post-secondary institutions to increase the number of and diversity of incoming applications through the utilization of gaming and gaming approaches in the recruitment process while staying low-cost. This propelling question guided the group through their work. The team’s work primarily focused on recruitment efforts at Arizona State University, but the concept can be modified and applied at other post-secondary institutions. The initial research showed that Arizona State University’s recruitment focused on visiting the high schools of prospective students and providing campus tours to interested students. A proposed alternative solution to aid in recruitment efforts through the utilization of gaming was to create an online multiplayer game that prospective students could play from their own homes. The basic premise of the game is that one player is selected to be “the Professor” while the other players are part of “the Students.” To complete the game, The Students must complete a set of tasks while the Professor applies various obstacles to prevent the Students from winning. When a Student completes their objectives, they win and the game ends. The game was created using Unity. The group has completed a proof-of-concept of the proposed game and worked to advertise and market the game to students via social media. The team’s efforts have gained traction and the group continues to work to gain traction and bring the idea to more prospective students.

ContributorsCole, Tyler Phillip (Co-author) / Ouellette, Abigail (Co-author) / Dong, Edmund E. (Co-author) / Byrne, Jared (Thesis director) / Pierce, John (Committee member) / Software Engineering (Contributor) / Department of Finance (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description

In this thesis, several different methods for detecting and removing satellite streaks from astronomic images were evaluated and compared with a new machine learning based approach. Simulated data was generated with a variety of conditions, and the performance of each method was evaluated both quantitatively, using Mean Absolute Error (MAE)

In this thesis, several different methods for detecting and removing satellite streaks from astronomic images were evaluated and compared with a new machine learning based approach. Simulated data was generated with a variety of conditions, and the performance of each method was evaluated both quantitatively, using Mean Absolute Error (MAE) against a ground truth detection mask and processing throughput of the method, as well as qualitatively, examining the situations in which each model performs well and poorly. Detection methods from existing systems Pyradon and ASTRiDE were implemented and tested. A machine learning (ML) image segmentation model was trained on simulated data and used to detect streaks in test data. The ML model performed favorably relative to the traditional methods tested, and demonstrated superior robustness in general. However, the model also exhibited some unpredictable behavior in certain scenarios which should be considered. This demonstrated that machine learning is a viable tool for the detection of satellite streaks in astronomic images, however special care must be taken to prevent and to minimize the effects of unpredictable behavior in such models.

ContributorsJeffries, Charles (Author) / Acuna, Ruben (Thesis director) / Martin, Thomas (Committee member) / Bansal, Ajay (Committee member) / Barrett, The Honors College (Contributor) / Software Engineering (Contributor)
Created2023-05
165938-Thumbnail Image.png
Description

This paper will demonstrate that the Agile development process helps to ensure incremental work on an Unreal Engine game project is achieved by presenting a product produced in Unreal Engine along with my experience in utilizing Scrum to facilitate the game’s development. Section 2 discusses project goals and motivations for

This paper will demonstrate that the Agile development process helps to ensure incremental work on an Unreal Engine game project is achieved by presenting a product produced in Unreal Engine along with my experience in utilizing Scrum to facilitate the game’s development. Section 2 discusses project goals and motivations for using Agile, using Unreal Engine, and for the choice of genre in the final product. Section 3 contextualizes these goals by presenting the history of Unreal Engine, the novel applications of Unreal Engine, and the use of Unreal Engine in the development of Heady Stuff. Section 4 presents findings from the project’s development by describing my use of Agile and by presenting the steps taken in learning Unreal Engine. Section 4 continues by highlighting important development considerations in the use of Blueprints, C++, and HLSL in Unreal Engine. The section ends with the presentation of project feedback, its incorporation in the final product, and the resources used to assist development. Section 5 compares the workflow, help resources, and applications of Unreal Engine with those of Unity, another highly popular game engine. Lastly, Section 6 performs a post-mortem on the overall development process by considering how well Agile development processes were upheld along with how much of the original plans in the Design Document was present in the final product. Additionally, the section presents the major challenges encountered during project development. These challenges will help in proposing possible best practices for game development in Unreal Engine.

ContributorsHreshchyshyn, Jacob (Author) / Acuna, Ruben (Thesis director) / Hentges, John (Committee member) / Barrett, The Honors College (Contributor) / Software Engineering (Contributor) / Computing and Informatics Program (Contributor)
Created2022-05