@inproceedings{e9df071fab854e8cbe1a014a9caf27ea,
title = "Trajectory optimization using dynamic programming and Q-learning",
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.",
keywords = "DP, MDP, optimization, Q-learning",
author = "Lee, \{Jeong Han\} and Lee, \{Jae Suk\}",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th IEEE Student Conference on Electric Machines and Systems, SCEMS 2022 ; Conference date: 24-11-2022 Through 26-11-2022",
year = "2022",
doi = "10.1109/SCEMS56272.2022.9990639",
language = "English",
series = "SCEMS 2022 - 2022 IEEE 5th Student Conference on Electric Machines and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "SCEMS 2022 - 2022 IEEE 5th Student Conference on Electric Machines and Systems",
}