Show simple item record

dc.contributor.advisorIsbell, Charles L
dc.contributor.authorSchroecker, Yannick Karl Daniel
dc.date.accessioned2020-05-20T16:59:41Z
dc.date.available2020-05-20T16:59:41Z
dc.date.created2020-05
dc.date.issued2020-03-16
dc.date.submittedMay 2020
dc.identifier.urihttp://hdl.handle.net/1853/62755
dc.description.abstractImitation learning has emerged as one of the most effective approaches to train agents to act intelligently in unstructured and unknown domains. On its own or in combination with reinforcement learning, it enables agents to copy the expert's behavior and to solve complex, long-term decision making problems. However, to utilize demonstrations effectively and learn from a finite amount of data, the agent needs to develop an understanding of the environment. This thesis investigates estimators of the state-distribution gradient as a means to influence which states the agent will see and thereby guide it to imitate the expert's behavior. Furthermore, this thesis will show that approaches which reason over future states in this way are able to learn from sparse signals and thus provide a way to effectively program agents. Specifically, this dissertation aims to validate the following thesis statement: Exploiting inherent structure in Markov chain stationary distributions allows learning agents to reason about likely future observations, and enables robust and efficient imitation learning, providing an effective and interactive way to teach agents from minimal demonstrations.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectImitation learning
dc.subjectReinforcement learning
dc.subjectDeep learning
dc.subjectMachine learning
dc.subjectArtificial intelligence
dc.titleManipulating state space distributions for sample-efficient imitation-learning
dc.typeDissertation
dc.description.degreePh.D.
dc.contributor.departmentInteractive Computing
thesis.degree.levelDoctoral
dc.contributor.committeeMemberChernova, Sonia
dc.contributor.committeeMemberBoots, Byron
dc.contributor.committeeMemberEssa, Irfan
dc.contributor.committeeMemberde Freitas, Nando
dc.date.updated2020-05-20T16:59:41Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record