Research on Strategy Generation for Orbital Games with Variable Decision Cycles

Chengzi Guan; Yao Zhang; Hongbo Wang; Shuya Tang; Yazhou Yang; Shihao Feng

doi:10.1016/j.ifacol.2025.11.456

Research on Strategy Generation for Orbital Games with Variable Decision Cycles

Chengzi Guan^*
, Yao Zhang^*
, Hongbo Wang^*
, Shuya Tang^*
, Yazhou Yang^*
, Shihao Feng^*

^*Corresponding author for this work

Beijing Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

Abstract

To address the limitations of fixed-cycle strategies in uncertain orbital pursuit-evasion games, this study proposes a hierarchical network reinforcement learning approach for variable-cycle decision-making. Firstly, pulse-thrust-controlled spacecraft dynamics and a variable-cycle game environment are constructed, followed by the design of a dual-network architecture to generate actions across heterogeneous decision cycles. Finally, the strategy is trained in simulation, enabling strategy convergence, with cumulative reward trajectories validating the effectiveness of the method.

Original language	English
Pages (from-to)	2024-2029
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	59
Issue number	20
DOIs	https://doi.org/10.1016/j.ifacol.2025.11.456
Publication status	Published - 1 Aug 2025
Externally published	Yes
Event	23th IFAC Symposium on Automatic Control in Aerospace, ACA 2025 - Harbin, China Duration: 2 Aug 2025 → 6 Aug 2025

Keywords

Control algorithms implementation
Decision making and autonomy
guidance and control
navigation
Spacecraft
Spacecraft dynamics

Access to Document

10.1016/j.ifacol.2025.11.456

Cite this

@article{f814625e114b4c5582cc623face27da2,

title = "Research on Strategy Generation for Orbital Games with Variable Decision Cycles",

abstract = "To address the limitations of fixed-cycle strategies in uncertain orbital pursuit-evasion games, this study proposes a hierarchical network reinforcement learning approach for variable-cycle decision-making. Firstly, pulse-thrust-controlled spacecraft dynamics and a variable-cycle game environment are constructed, followed by the design of a dual-network architecture to generate actions across heterogeneous decision cycles. Finally, the strategy is trained in simulation, enabling strategy convergence, with cumulative reward trajectories validating the effectiveness of the method.",

keywords = "Control algorithms implementation, Decision making and autonomy, guidance and control, navigation, Spacecraft, Spacecraft dynamics",

author = "Chengzi Guan and Yao Zhang and Hongbo Wang and Shuya Tang and Yazhou Yang and Shihao Feng",

note = "Publisher Copyright: Copyright {\textcopyright} 2025 The Authors.; 23th IFAC Symposium on Automatic Control in Aerospace, ACA 2025 ; Conference date: 02-08-2025 Through 06-08-2025",

year = "2025",

month = aug,

day = "1",

doi = "10.1016/j.ifacol.2025.11.456",

language = "English",

volume = "59",

pages = "2024--2029",

journal = "IFAC-PapersOnLine",

issn = "2405-8963",

publisher = "Elsevier B.V.",

number = "20",

}

TY - JOUR

T1 - Research on Strategy Generation for Orbital Games with Variable Decision Cycles

AU - Guan, Chengzi

AU - Zhang, Yao

AU - Wang, Hongbo

AU - Tang, Shuya

AU - Yang, Yazhou

AU - Feng, Shihao

PY - 2025/8/1

Y1 - 2025/8/1

N2 - To address the limitations of fixed-cycle strategies in uncertain orbital pursuit-evasion games, this study proposes a hierarchical network reinforcement learning approach for variable-cycle decision-making. Firstly, pulse-thrust-controlled spacecraft dynamics and a variable-cycle game environment are constructed, followed by the design of a dual-network architecture to generate actions across heterogeneous decision cycles. Finally, the strategy is trained in simulation, enabling strategy convergence, with cumulative reward trajectories validating the effectiveness of the method.

AB - To address the limitations of fixed-cycle strategies in uncertain orbital pursuit-evasion games, this study proposes a hierarchical network reinforcement learning approach for variable-cycle decision-making. Firstly, pulse-thrust-controlled spacecraft dynamics and a variable-cycle game environment are constructed, followed by the design of a dual-network architecture to generate actions across heterogeneous decision cycles. Finally, the strategy is trained in simulation, enabling strategy convergence, with cumulative reward trajectories validating the effectiveness of the method.

KW - Control algorithms implementation

KW - Decision making and autonomy

KW - guidance and control

KW - navigation

KW - Spacecraft

KW - Spacecraft dynamics

UR - https://www.scopus.com/pages/publications/105025914266

U2 - 10.1016/j.ifacol.2025.11.456

DO - 10.1016/j.ifacol.2025.11.456

M3 - Conference article

AN - SCOPUS:105025914266

SN - 2405-8963

VL - 59

SP - 2024

EP - 2029

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 20

T2 - 23th IFAC Symposium on Automatic Control in Aerospace, ACA 2025

Y2 - 2 August 2025 through 6 August 2025

ER -

Research on Strategy Generation for Orbital Games with Variable Decision Cycles

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this