TY  - JOUR
AU  - Guo, Tao
AU  - Wu, Rongxin
AU  - Yi, Hui
AU  - Jiang, Huilin
PY  - 2026
DA  - 2026/06/27
TI  - A Review of Dynamic Resource Allocation Techniques for Integrated Sensing, Communication, and Computing Networks Based on Deep Reinforcement Learning
JO  - ICCK Transactions on Intelligent Cyber-Physical Systems
T2  - ICCK Transactions on Intelligent Cyber-Physical Systems
JF  - ICCK Transactions on Intelligent Cyber-Physical Systems
VL  - 1
IS  - 2
SP  - 76
EP  - 82
DO  - 10.62762/TICPS.2026.591816
UR  - https://www.icck.org/article/abs/TICPS.2026.591816
KW  - integrated sensing, communication, and computing (ISCC)
KW  - deep reinforcement learning
KW  - dynamic resource allocation
KW  - multi-agent reinforcement learning
KW  - 6G network
AB  - The integrated sensing, communication, and computing (ISCC) network, as a core direction of the sixth-generation mobile communication system, provides a key enabling technology for efficient collaboration in future intelligent networks by deeply integrating communication, sensing, and computing capabilities. However, the dynamic management and joint optimization of multi-dimensional heterogeneous resources in ISCC networks face severe challenges such as high-dimensional state spaces, tightly coupled constraints, and time-varying environments. Traditional optimization methods struggle to achieve both real-time performance and optimality. Deep reinforcement learning (DRL), with its end-to-end learning capability for complex sequential decision-making problems, offers a novel solution to this dilemma. This paper systematically reviews the current research status of dynamic resource allocation in ISCC networks. It analyzes the fundamental background and resource management challenges of ISCC networks, reviews representative domestic and international research advances in DRL-based resource allocation covering both single-agent and multi-agent approaches, and provides a critical discussion of existing limitations and future research directions.
SN  - 3071-2947
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Guo2026A,
  author = {Tao Guo and Rongxin Wu and Hui Yi and Huilin Jiang},
  title = {A Review of Dynamic Resource Allocation Techniques for Integrated Sensing, Communication, and Computing Networks Based on Deep Reinforcement Learning},
  journal = {ICCK Transactions on Intelligent Cyber-Physical Systems},
  year = {2026},
  volume = {1},
  number = {2},
  pages = {76-82},
  doi = {10.62762/TICPS.2026.591816},
  url = {https://www.icck.org/article/abs/TICPS.2026.591816},
  abstract = {The integrated sensing, communication, and computing (ISCC) network, as a core direction of the sixth-generation mobile communication system, provides a key enabling technology for efficient collaboration in future intelligent networks by deeply integrating communication, sensing, and computing capabilities. However, the dynamic management and joint optimization of multi-dimensional heterogeneous resources in ISCC networks face severe challenges such as high-dimensional state spaces, tightly coupled constraints, and time-varying environments. Traditional optimization methods struggle to achieve both real-time performance and optimality. Deep reinforcement learning (DRL), with its end-to-end learning capability for complex sequential decision-making problems, offers a novel solution to this dilemma. This paper systematically reviews the current research status of dynamic resource allocation in ISCC networks. It analyzes the fundamental background and resource management challenges of ISCC networks, reviews representative domestic and international research advances in DRL-based resource allocation covering both single-agent and multi-agent approaches, and provides a critical discussion of existing limitations and future research directions.},
  keywords = {integrated sensing, communication, and computing (ISCC), deep reinforcement learning, dynamic resource allocation, multi-agent reinforcement learning, 6G network},
  issn = {3071-2947},
  publisher = {Institute of Central Computation and Knowledge}
}