University of Arkansas, Fayetteville ScholarWorks@UARK Computer Science and Computer Engineering Undergraduate Honors Theses Computer Science and Computer Engineering 5-2020 Applying Imitation and Reinforcement Learning to Sparse Reward Environments Haven Brown Follow this and additional works at: https://scholarworks.uark.edu/csceuht Part of the Artificial Intelligence and Robotics Commons, Software Engineering Commons, and the Theory and Algorithms Commons Citation Brown, H. (2020). Applying Imitation and Reinforcement Learning to Sparse Reward Environments. Computer Science and Computer Engineering Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/csceuht/79 This Thesis is brought to you for free and open access by the Computer Science and Computer Engineering at ScholarWorks@UARK. It has been accepted for inclusion in Computer Science and Computer Engineering Undergraduate Honors Theses by an authorized administrator of ScholarWorks@UARK. For more information, please contact
[email protected]. Applying Imitation and Reinforcement Learning to Sparse Reward Environments An honors thesis submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science with Honors by Haven Brown University of Arkansas Candidate for Bachelors of Science in Computer Science, 2020 Candidate for Bachelors of Science in Mathematics, 2020 May 2020 University of Arkansas This honors thesis is approved for recommendation to the CSCE thesis defense committee. David Andrews, PhD Dissertation Director John Gauch, PhD Lora Streeter, PhD Committee Member Committee Member Abstract The focus of this project was to shorten the time it takes to train reinforcement learn- ing agents to perform better than humans in a sparse reward environment. Finding a general purpose solution to this problem is essential to creating agents in the future ca- pable of managing large systems or performing a series of tasks before receiving feedback.