Show simple item record

dc.contributor.advisorIsbell, Charles L.
dc.contributor.authorEdwards, Ashley Deloris
dc.date.accessioned2019-05-29T14:02:27Z
dc.date.available2019-05-29T14:02:27Z
dc.date.created2019-05
dc.date.issued2019-04-02
dc.date.submittedMay 2019
dc.identifier.urihttp://hdl.handle.net/1853/61234
dc.description.abstractThis dissertation aims to demonstrate how perceptual goal specifications may be used as alternative representations for specifying domain-specific reward functions for reinforcement learning. The works outlined in this document aim to validate the following thesis statement: Employing perceptual goal specifications for goal-directed tasks: is as straightforward as specifying domain-specific rewards; is a more general representation for tasks; and equally enables task completion. We describe various approaches for specifying goals visually and how we may compute rewards and learn policies directly from these representations. Chapter 4 introduces Perceptual Reward Functions and describes how we can utilize a hand-defined similarity metric to enable learning from goals that are different from an agent’s. Chapter 5 introduces Cross-Domain Perceptual Reward Functions and describes how we can learn a reward function for cross-domain goal specifications. Chapter 6 introduces Perceptual Value Functions and describes how we can learn a value function from sequences of expert observations without access to ground-truth actions. Chapter 7 introduces Latent Policy Networks and describes how we can learn a policy from sequences of expert observations without access to ground-truth actions. The remaining chapters motivate and provide background for this dissertation and outline a plan for future research.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectReinforcement learning
dc.subjectGoal specification
dc.subjectImitation learning
dc.subjectReward design
dc.titleEmulation and imitation via perceptual goal specifications
dc.typeDissertation
dc.description.degreePh.D.
dc.contributor.departmentComputer Science
thesis.degree.levelDoctoral
dc.contributor.committeeMemberBalch, Tucker
dc.contributor.committeeMemberChernova, Sonia
dc.contributor.committeeMemberRiedl, Mark
dc.contributor.committeeMemberAbbeel, Pieter
dc.date.updated2019-05-29T14:02:27Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record