Incremental multi-step Q-learning
Machine Learning - Special issue on reinforcement learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
The Impact of Data Aggregation in Wireless Sensor Networks
ICDCSW '02 Proceedings of the 22nd International Conference on Distributed Computing Systems
On Localized Prediction for Power Efficient Object Tracking in Sensor Networks
ICDCSW '03 Proceedings of the 23rd International Conference on Distributed Computing Systems
Dynamic Programming
Power conservation and quality of surveillance in target tracking sensor networks
Proceedings of the 10th annual international conference on Mobile computing and networking
IEEE Communications Magazine
| Hi-index | 0.00 |
In this paper, we consider a target-tracking sensor network and improve its energy awareness through predicting a target trajectory and decreasing sampling rate of sensors while maintaining an acceptable tracking accuracy. The tracking problem is formulated as a hierarchical Markov decision process (MDP) and is solved through neurodynamic programming. Though this is not new, improvements in performance of the network are achieved by use of a reinforcement learning algorithm to solve the MDP that converges faster than the preceding used methods, since the energy efficiency and speed of convergence of the solution are tightly coupled. Simulation results show the effectiveness of our algorithm against other known target tracking algorithms.