Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

Feudal Networks for Hierarchical Reinforcement Learning Revisited

Augenstein, Alexander S. (2019) Feudal Networks for Hierarchical Reinforcement Learning Revisited. Master's Thesis, University of Pittsburgh. (Unpublished)

This is the latest version of this item.

[img]
Preview
 PDF (augensteinas_etdPitt03302019)
Submitted Version
Download (1MB) | Preview

Abstract

Hierarchical Reinforcement Learning (RL) has gained popularity in recent years in designing RL algorithms that converge in complex environments. Convergence of RL algorithms remains an active area of research, and no single approach has been found to work for all RL applications. Feudal networks (FuNs) are a hierarchical RL technique attempting to address portability and other problems by defining an internal structure for an RL agent using a Manager-Worker hierarchy. A Manager is that portion of the system utilizing a low temporal resolution component for setting goals to maximize rewards from the environment, while the Worker utilizes a high temporal resolution component for selecting among action primitives to maximize rewards from the Manager. This thesis provides an overview of reinforcement learning and the FuN architecture, then compares the relative convergence rates of untrained FuNs to FuNs constructed by Workers with different physical embodiments under a trained Manager.

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Augenstein, Alexander S.asa55@pitt.eduasa55
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorMao, Zhi-Hongzhm4@pitt.eduzhm4
Committee ChairMao, Zhi-Hongzhm4@pitt.eduzhm4
Committee MemberZhan, Liangliang.zhan@pitt.edu
Committee MemberDallal, Ahmed H. S.ahd12@pitt.eduahd12
Date: 18 June 2019
Date Type: Publication
Defense Date: 26 March 2019
Approval Date: 18 June 2019
Submission Date: 5 March 2019
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 60
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Electrical and Computer Engineering
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: feudal networks, reinforcement learning, machine learning, hierarchical reinforcement learning
Date Deposited: 18 Jun 2019 17:15
Last Modified: 18 Jun 2019 17:15
URI: http://d-scholarship.pitt.edu/id/eprint/36179

Available Versions of this Item

  • Feudal Networks for Hierarchical Reinforcement Learning Revisited. (deposited 18 Jun 2019 17:15) [Currently Displayed]

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item