Cooperation Between Multiple Agents Based on Partially Sharing Policy

Hwang, Kao-Shing; Lin, Chia‐Ju; Wu, Chun-Ju; Lo, Chia-Yue

doi:10.1007/978-3-540-74171-8_42

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, classical learning algorithms, such as Q-learning, have been modified to achieve better conversion. The Win of Learn Fast Policy Hill Climbing (WoLF-PHC) algorithm is proposed as an extension of the Q-learning algorithm for more efficient learning of the dynamic target [19]. Its characteristic is the use of different learning rates depending on the game outcome, which increases the convergence in multi-agent non-stationary environment.…”

Section: Multi-agent Reinforcement Learning Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Blockchain-Based Network Slice Broker to Facilitate Factory-As-a-Service

Hewa

Porambage

Kovacevic

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

The novel concept of Factory-as-a-Service (FaaS) allows the agility of adapting the manufacturing process by identifying the industry's supply chain and user requirements. To cater to FaaS, flexibility in networking and cloud services is a must. 5G network slice broker is a third-party mediator that caters to networking resource demand from clients to the service providers. Thus, this paper introduces a secure blockchain-based network slice broker to facilitate FaaS. The proposed secure network slice broker (SNSB) provides secure, cognitive, and distributed network services for resource allocation and security service level agreement (SSLA) formation with coordination of slice managers and SSLA managers. In SNSB we introduce a federated slice selection algorithm with Stackelberg game model and Reinforcement Learning (RL) algorithm to compute the realtime and the optimal unit price and demand level. We provide an extensive implementation and performance evaluation of SNSB using the Katana slice manager and a custom SSLA manager.

show abstract

Section: Multi-agent Reinforcement Learning Algorithmmentioning

confidence: 99%

“…In the course of the learning process, the chance of the fog node selecting a service demand is progressively increased, which can elevate the expected reward, followed by the reduction of the other actions [19]. Hence, the update of the service demand policy of the fog node can be presented as follows,…”

Section: Multi-agent Reinforcement Learning Algorithmmentioning

confidence: 99%