PhD Defense by Zheyuan Wang

Event Details
  • Date/Time:
    • Wednesday December 7, 2022
      9:00 am - 11:00 am
  • Location: REMOTE
  • Phone:
  • URL: Zoom
  • Email:
  • Fee(s):
    N/A
  • Extras:
Contact
No contact information submitted.
Summaries

Summary Sentence: Learning Dynamic Priority Scheduling Policies with Graph Attention Networks

Full Summary: No summary paragraph submitted.

Title:  Learning Dynamic Priority Scheduling Policies with Graph Attention Networks

 

Date: Wednesday, December 7, 2022

Time: 9 a.m. – 11 a.m. ET

Location: https://gatech.zoom.us/j/97223685875

 

Zheyuan Wang

PhD Candidate

School of Electrical and Computer Engineering

Georgia Institute of Technology

 

 Committee

Dr. Matthew Gombolay (Advisor) - School of Interactive Computing, Georgia Institute of Technology

Dr. Matthieu Bloch (Co-Advisor) - School of Electrical and Computer Engineering, Georgia Institute of Technology

Dr. Sonia Chernova - School of Interactive Computing, Georgia Institute of Technology

Dr. Magnus Egerstedt - Department of Electrical Engineering and Computer Science, University of California, Irvine

Dr. Harish Ravichandar - School of Interactive Computing, Georgia Institute of Technology

Dr. Elias Khalil - Department of Mechanical and Industrial Engineering, University of Toronto

 

Abstract

The aim of this thesis is to develop novel graph attention network-based models to automatically learn scheduling policies for effectively solving resource optimization problems, covering both deterministic and stochastic environments. The policy learning methods utilize both imitation learning, when expert demonstrations are accessible at low cost, and reinforcement learning, when otherwise reward engineering is feasible. By parameterizing the learner with graph attention networks, the framework is computationally efficient and results in scalable resource optimization schedulers that adapt to various problem structures. This thesis addresses the problem of multi-robot task allocation (MRTA) under temporospatial constraints. Initially, robots with deterministic and homogeneous task performance are considered with the development of the RoboGNN scheduler. Then, I develop ScheduleNet, a novel heterogeneous graph attention network model, to efficiently reason about coordinating teams of heterogeneous robots. Next, I address problems under the more challenging stochastic setting in two parts. Part 1) Scheduling with stochastic and dynamic task completion times. The MRTA problem is extended by introducing human coworkers with dynamic learning curves and stochastic task execution. HybridNet, a hybrid network structure, has been developed that utilizes a heterogeneous graph-based encoder and a recurrent schedule propagator, to carry out fast schedule generation in multi-round settings. Part 2) Scheduling with stochastic and dynamic task arrival and completion times. With an application in failure-predictive plane maintenance, I develop a heterogeneous graph-based policy optimization (HetGPO) approach to enable learning robust scheduling policies in highly stochastic environments. Through extensive experiments, the proposed framework has been shown to outperform prior state-of-the-art algorithms in different applications. My research contributes several key innovations regarding designing graph-based learning algorithms in operations research.

Additional Information

In Campus Calendar
No
Groups

Graduate Studies

Invited Audience
Faculty/Staff, Public, Undergraduate students
Categories
Other/Miscellaneous
Keywords
Phd Defense
Status
  • Created By: Tatianna Richardson
  • Workflow Status: Published
  • Created On: Dec 5, 2022 - 5:37pm
  • Last Updated: Dec 5, 2022 - 5:37pm