Bittner, Nathan2019-10-162019-10-162018-05-12https://hdl.handle.net/11299/208537In this thesis, I present advancements in the theory of Z-learning. In particular, I explicitly define a complete tabular Z-learning algorithm, I provide a number of pragmatic qualifications on how Z-learning should be applied to different problem domains, and I extend Z-learning to non-tabular discrete domains by introducing deep network function-approximation versions of Z-learning that is similar to deep Q-learningenDeep LearningReinforcement LearningSumma Cum LaudeComputer ScienceCollege of Science and EngineeringThesis or Dissertation