Subtask-masked curriculum learning for reinforcement learning with application to UAV maneuver decision-making

Journal Article (2023)
Author(s)

Yueqi Hou (Air Force Engineering University China)

Xiaolong Liang (Air Force Engineering University China)

Maolong Lv (Air Force Engineering University China)

Qisong Yang (TU Delft - Algorithmics)

Yang Li (TU Delft - Algorithmics)

Research Group
Algorithmics
Copyright
© 2023 Yueqi Hou, Xiaolong Liang, Maolong Lv, Q. Yang, Y. Li
DOI related publication
https://doi.org/10.1016/j.engappai.2023.106703
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Yueqi Hou, Xiaolong Liang, Maolong Lv, Q. Yang, Y. Li
Research Group
Algorithmics
Volume number
125
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Unmanned Aerial Vehicle (UAV) maneuver strategy learning remains a challenge when using Reinforcement Learning (RL) in this sparse reward task. In this paper, we propose Subtask-Masked curriculum learning for RL (SUBMAS-RL), an efficient RL paradigm that implements curriculum learning and knowledge transfer for UAV maneuver scenarios involving multiple missiles. First, this study introduces a novel concept known as subtask mask to create source tasks from a target task by masking partial subtasks. Then, a subtask-masked curriculum generation method is proposed to generate a sequenced curriculum by alternately conducting task generation and task sequencing. To establish efficient knowledge transfer and avoid negative transfer, this paper employs two transfer techniques, policy distillation and policy reuse, along with an explicit transfer condition that masks irrelevant knowledge. Experimental results demonstrate that our method achieves a 94.8% success rate in the UAV maneuver scenario, where the direct use of reinforcement learning always fails. The proposed RL framework SUBMAS-RL is expected to learn an effective policy in complex tasks with sparse rewards.

Files

1_s2.0_S0952197623008874_main.... (pdf)
(pdf | 2.35 Mb)
- Embargo expired in 01-01-2024
License info not available