Behavior Shaping and Analysis in Multi-Agent Reinforcement Learning: Experiments in Combat Tactics and Survivability

dc.contributor.advisorAlamaniotis, Miltos
dc.contributor.advisorHolladay, Kenneth
dc.contributor.authorHall, Garrett
dc.contributor.committeeMemberRad, Paul
dc.contributor.committeeMemberGriffith, Henry
dc.date.accessioned2024-02-09T21:56:13Z
dc.date.available2024-02-09T21:56:13Z
dc.date.issued2022
dc.descriptionThis item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.
dc.description.abstractThe goal of Multi-Agent Reinforcement Learning (MARL) is to autonomously learn tasks without being explicitly programed to do so. Video games serve as an ideal environment for training MARL agents. This research uses the real-time strategy game StarCraft II (SC2) to explore how MARL agents solve their tasks, as well as various methods for shaping new agent behaviors. Chapter One introduces MARL and the motivation for using a video game environment for research. It also defines the working hypotheses that guided this work and how the research was carried out. Chapter Two provides a background for: • the theory behind multi-agent reinforcement learning; • behavioral cloning and transfer learning methods used to shape behaviors and improve agent performance; • a detailed description of the SC2 environment and the targeting system of the native SC2 AI; • how MARL agents can behave unexpectedly. Chapter Three discusses the general approach used to train the agents. Chapter Four provides an in-depth discussion of the design and results for each of the five experiments. Chapter Five concludes the work completed by this thesis with a summary of the results, a discussion of their importance, and future research activities. The MARL agents trained against a variety of adversaries in the SC2 environment. Principal discoveries from the five experiments include: • agents can improve survivability with proper rewards; • agents will develop new behaviors based on their enemies; • behaviors can be retained through transfer learning to be applied against new enemies; • agents who train with expert agents significantly reduce their training time.
dc.description.departmentElectrical and Computer Engineering
dc.format.extent70 pages
dc.format.mimetypeapplication/pdf
dc.identifier.isbn9798438756415
dc.identifier.urihttps://hdl.handle.net/20.500.12588/3697
dc.languageen
dc.subjectbehavior analysis
dc.subjectexploration and exploitation
dc.subjectmulti-agent
dc.subjectreinforcement learning
dc.subjectStarCraft II
dc.subject.classificationArtificial intelligence
dc.subject.classificationElectrical engineering
dc.titleBehavior Shaping and Analysis in Multi-Agent Reinforcement Learning: Experiments in Combat Tactics and Survivability
dc.typeThesis
dc.type.dcmiText
dcterms.accessRightspq_closed
thesis.degree.departmentElectrical and Computer Engineering
thesis.degree.grantorUniversity of Texas at San Antonio
thesis.degree.levelMasters
thesis.degree.nameMaster of Science

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Hall_utsa_1283M_13600.pdf
Size:
5.16 MB
Format:
Adobe Portable Document Format