Evaluating Flexibility Metrics on Simple Temporal Networks with Reinforcement Learning

Author

Hamzah I. Khan, Harvey Mudd CollegeFollow

Graduation Year

2018

Document Type

Open Access Senior Thesis

Degree Name

Bachelor of Science

Department

Mathematics

Reader 1

Susan E. Martonosi

Reader 2

James C. Boerkoel, Jr.

Terms of Use & License Information

Terms of Use for work posted in Scholarship@Claremont.

Rights Information

© 2018 Hamzah I. Khan

Abstract

Simple Temporal Networks (STNs) were introduced by Tsamardinos (2002) as a means of describing graphically the temporal constraints for scheduling problems. Since then, many variations on the concept have been used to develop and analyze algorithms for multi-agent robotic scheduling problems. Many of these algorithms for STNs utilize a flexibility metric, which measures the slack remaining in an STN under execution. Various metrics have been proposed by Hunsberger (2002); Wilson et al. (2014); Lloyd et al. (2018). This thesis explores how adequately these metrics convey the desired information by using them to build a reward function in a reinforcement learning problem.

Recommended Citation

Khan, Hamzah I., "Evaluating Flexibility Metrics on Simple Temporal Networks with Reinforcement Learning" (2018). HMC Senior Theses. 116.
https://scholarship.claremont.edu/hmc_theses/116

Source Fulltext

https://www.math.hmc.edu/~hkhan/thesis/