Skip to main navigation Skip to search Skip to main content

Trajectory optimization using dynamic programming and Q-learning

  • Jeong Han Lee*
  • , Jae Suk Lee
  • *Corresponding author for this work
  • Jeonbuk National University

Research output: Contribution to conferenceConference paperpeer-review

Abstract

This paper presents route optimization in Markov Decision Process (MDP) environment using dynamic programming (DP) and Q-learning, and compares features of two algorithms. Since DP uses recursive function, coding is simple and easy to implement. However, all cases should be calculated to implement DP. Due to this characteristic, the unnecessary calculation rate increases as the model grows for implementation of DP. In this paper, learning is applied to DP for reduction of calculation complexity. Same MDP problem is solved by DP and Q-learning and results of each case are compared and analyzed in this paper.

Original languageEnglish
Title of host publicationSCEMS 2022 - 2022 IEEE 5th Student Conference on Electric Machines and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665476898
DOIs
StatePublished - 2022
Event5th IEEE Student Conference on Electric Machines and Systems, SCEMS 2022 - Busan, Korea, Republic of
Duration: 2022.11.242022.11.26

Publication series

NameSCEMS 2022 - 2022 IEEE 5th Student Conference on Electric Machines and Systems

Conference

Conference5th IEEE Student Conference on Electric Machines and Systems, SCEMS 2022
Country/TerritoryKorea, Republic of
CityBusan
Period22.11.2422.11.26

Keywords

  • DP
  • MDP
  • optimization
  • Q-learning

Quacquarelli Symonds(QS) Subject Topics

  • Engineering - Mechanical
  • Engineering - Electrical & Electronic
  • Engineering - Petroleum

Fingerprint

Dive into the research topics of 'Trajectory optimization using dynamic programming and Q-learning'. Together they form a unique fingerprint.

Cite this