Show simple item record

dc.contributor.advisorBoots, Byron
dc.contributor.authorLiu, Anthony J.
dc.date.accessioned2021-06-30T17:37:07Z
dc.date.available2021-06-30T17:37:07Z
dc.date.created2020-05
dc.date.submittedMay 2020
dc.identifier.urihttp://hdl.handle.net/1853/64838
dc.description.abstractIn of optimal control and reinforcement learning, the difference in the performance of a state-of-the-art policy and a mediocre one is minuscule in comparison to their difference in amortized computational cost. Further, in certain situations the mediocre policy will be able to perform as well as the state-of-the-art policy, and it will all the while have used significantly less computational resources to do so. This phenomenon is a consequence of the necessity for additional compute to solve difficult scenarios; however, while sparsely occurring, these scenarios can be catastrophic for most planning tasks. In this work, we focus on addressing this imbalance between performance and computational cost in the context of planning. We combine ideas that have been prevalent in other machine learning problems and in Hierarchical Reinforcement Learning, and propose a Context-Aware Adaptive Policy Selector (CAAPS). We utilize our selector to create a meta-policy which can minimize these catastrophic states (thus maximizing the policy's ultimate performance), while also minimizing the computational cost necessary to run the policy. Our meta-policy accomplishes this by adaptively selecting from a set of pre-trained candidate policies which vary in performance and complexity, and we show that in certain environments we are able to plan trajectories at near-optimal performance while minimizing the amortized computational cost.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectReinforcement Learning
dc.subjectMeta Learning
dc.subjectPolicy Selector
dc.subjectOptimal Control
dc.subjectRobotics
dc.subjectOptimization
dc.subjectAdaptive Computation
dc.titleContext Aware Policy Selection
dc.typeUndergraduate Research Option Thesis
dc.description.degreeUndergraduate
dc.contributor.departmentComputer Science
thesis.degree.levelUndergraduate
dc.contributor.committeeMemberRiedl, Mark
dc.date.updated2021-06-30T17:37:07Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record