Reinforcement Learning Based Stochastic Shortest Path Finding in Wireless Sensor Networks

Reinforcement Learning Based Stochastic Shortest Path Finding in Wireless Sensor Networks

Many factors influence the connection states between nodes of wireless sensor networks, such as physical distance, and the network load, making the network's edge length dynamic in abundant scenarios. This dynamic property makes the network essentially form a graph with stochastic edge lengths....

Full description

Bibliographic Details
Main Authors: Wenwen Xia, Chong Di, Haonan Guo, Shenghong Li
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Stochastic shortest path finding
reinforcement learning
Q-learning
SARSA
convergence proof
Online Access:https://ieeexplore.ieee.org/document/8886484/

Internet

https://ieeexplore.ieee.org/document/8886484/

Similar Items