Generative Adversarial Network-Based Transfer Reinforcement Learning for Routing With Prior Knowledge

Dong, Tianjian; Qi, Qi; Wang, Jingyu; Liu, Alex X.; Sun, Haifeng; Zhuang, Zirui; Liao, Jianxin

doi:10.1109/tnsm.2021.3077249

Cited by 20 publications

(18 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining DGMs with DRL is proven to address this concern efficiently. For instance, Dong et al [7] present a GAN-empowered DRL approach for rapidly transferring routing knowledge from S to T . To do so, a generator G S is first trained to extract R S , the latent representation of S. Then, they train a DRL model, learning the routing strategies based on R S rather than S. If the state structure changes to T , another generator G T is used for generating R T .…”

Section: E Use Casesmentioning

confidence: 99%

Deep Generative Model and Its Applications in Efficient Wireless Network Management: A Tutorial and Case Study

Liu¹,

Du²,

Niyato³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: E Use Casesmentioning

confidence: 99%

Deep Generative Model and Its Applications in Efficient Wireless Network Management: A Tutorial and Case Study

Liu¹,

Du²,

Niyato³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For instance, as a network economic approach, the contract theory helps design fair contracts between clients and service providers regarding provided service and the reward, which is significant for incentivizing the participation and improving the operational quality [6]. For decision-making problems in wireless networks (e.g., resource allocation), DRL is regarded as one of the most efficient solutions [7], [8]. Using a Markov decision process, DRL models enable the agents to learn the optimal action under the given state by setting different rewards.…”

Section: B Major Issues In Wireless Network Managementmentioning

confidence: 99%

“…The structure of network states, i.e., the number and connectivity of devices, changes accordingly. Traditional approaches, e.g., DRL, cannot well fit such mobility [7]. Recall that DRL models are trained to select the optimal action in the given state.…”

Section: B Major Issues In Wireless Network Managementmentioning

confidence: 99%

“…Moreover, the management objective, i.e., minimizing the communication latency, should also be formulated. 7]. Note that this step mainly applies for learning-based approaches, e.g., DRL.…”

Section: Dgm-empowered Efficient Wireless Network Managementmentioning

confidence: 99%

“…Combining DGMs with DRL is proven to address this concern efficiently. For instance, Dong et al [7] present a GAN-based DRL approach for rapidly transferring routing knowledge from S to T . To do so, a generator G S is first trained to extract R S , the latent representation of S. Then, they train a DRL model, learning the routing strategies based on R S rather than S. If the state structure changes to T , another generator G T is used for generating R T .…”

Section: E Use Casesmentioning

confidence: 99%

See 2 more Smart Citations

A Study Of Civil Engineering Education At Singapore Nanyang Technology University And At The University Of Florida

Liu¹,

Najafi²

2002 Annual Conference Proceedings

View full text Add to dashboard Cite

offer civil engineering courses to undergraduate and graduate students. This paper discusses and compares Civil Engineering curriculum in both Universities. The Civil Engineering courses at the University of Florida are divided into two phases of general education and upper division/civil engineering core education. At Nanyang Technology University, the Civil Engineering offers courses of a prescribed core of essential subjects and both institutions offer excellent program of study. The Civil Engineering program at Nanyang Technology University offers courses closely related to industry and government needs. Similarly, at the University of Florida, Civil Engineering program also offers excellent education program in line with government and industries needs. At both institutions, efforts should be focused on revising curriculum that is more responsible to existing and future rapid technological changes.

show abstract

Hedge transfer learning routing for dynamic searching and reconnoitering applications in 3D multimedia FANETs

Zhang

Liu

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

With the fast development of unmanned aerial vehicles (UAVs) and the user increasing demand of UAV video transmission, UAV video service is widely used in dynamic searching and reconnoitering applications. Video transmissions not only consider the complexity and instability of 3D UAV network topology but also ensure reliable quality of service (QoS) in flying ad hoc networks (FANETs). We propose hedge transfer learning routing (HTLR) for dynamic searching and reconnoitering applications to address this problem. Compared with the previous transfer learning framework, HTRL has the following innovations. First, hedge principle is introduced into transfer learning. Online model is continuously trained on the basis of offline model, and their weight factors are adjusted in real-time by transfer learning, so as to adapt to the complex 3D FANETs. Secondly, distributed multi-hop link state scheme is used to estimate multi-hop link states in the whole network, thus enhancing the stability of transmission links. Among them, we propose the multiplication rule of multi-hop link states, which is a new idea to evaluate link states. Finally, we use packet delivery rate (PDR) and energy efficiency rate (EER) as two main evaluation metrics. In the same NS3 experimental scenario, the PDR of HTLR is at least 5.11% higher and the EER is at least 1.17 lower than compared protocols. Besides, we use Wilcoxon test to compare HTLR with the simplified version of HTLR without hedge transfer learning (N-HTLR). The results show that HTRL is superior to N-HTRL, effectively ensuring QoS.

show abstract

Generative Adversarial Network-Based Transfer Reinforcement Learning for Routing With Prior Knowledge

Cited by 20 publications

References 51 publications

Deep Generative Model and Its Applications in Efficient Wireless Network Management: A Tutorial and Case Study

Deep Generative Model and Its Applications in Efficient Wireless Network Management: A Tutorial and Case Study

A Study Of Civil Engineering Education At Singapore Nanyang Technology University And At The University Of Florida

Hedge transfer learning routing for dynamic searching and reconnoitering applications in 3D multimedia FANETs

Contact Info

Product

Resources

About