Disentangling the Octopus: Towards Decomposing Reinforcement Learning Systems in to Intuitive Subsystems

Loading...

View/Download File

Blum_umn_0130M_22210.pdf (691.52 KB)

Persistent link to this item

https://hdl.handle.net/11299/223101

Statistics

View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Disentangling the Octopus: Towards Decomposing Reinforcement Learning Systems in to Intuitive Subsystems

Authors

Blum, Carter

Published Date

2020-12

Publisher

Type

Thesis or Dissertation

Abstract

As electric vehicles have surged in popularity, the problem of ensuring that there issufficient infrastructure to charge them has attracted large amounts of interest. A key component of this is leveraging existing electric vehicle charging station capacity by intelligently recommending drivers to nearby open stations so they can recharge quickly. Greedily approaching such recommendations can quickly lead to long wait times, so this thesis proposes a method using reinforcement learning to provide recommendations to drivers. While common deep reinforcement learning models fail, exploiting regularities in the state space allows the problem to be decomposed in to smaller problems that can be modeled separately. Experiments demonstrate that this method not only decreases the time before vehicles can start charging by up to 47%, but also that decomposing the problem allows recommendations to be given 2.5x faster than other deep learning based models.

Keywords

Machine Learning

Reinforcement Learning

Description

University of Minnesota M.S. thesis. December 2020. Major: Computer Science. Advisor: Paul Schrater. 1 computer file (PDF); viii, 58 pages.

Related to

Replaces

License

Collections

Master's Theses (Plan A and Professional Engineering Design Projects)

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Suggested citation

Blum, Carter. (2020). Disentangling the Octopus: Towards Decomposing Reinforcement Learning Systems in to Intuitive Subsystems. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/223101.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.