Journal of the ACM (JACM)
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Sparse Distributed Memory
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
An algorithm for solving semi-markov decision problems using reinforcement learning: convergence analysis and numerical results
Joint Adoption of QoS Schemes for MPEG Streams
Multimedia Tools and Applications
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
EURO-NGI'05 Proceedings of the Second international conference on Wireless Systems and Network Architectures in Next Generation Internet
Scheduling scheme for providing QoS to real-time multimedia traffics in high-rate wireless PANs
IEEE Transactions on Consumer Electronics
MPEG-4 and H.263 video traces for network performance evaluation
IEEE Network: The Magazine of Global Internetworking
Computer Networks: The International Journal of Computer and Telecommunications Networking
Hi-index | 0.00 |
The emerging high-rate wireless personal area network (WPAN) technology is capable of supporting high-speed and high-quality real-time multimedia applications. In particular, video streams are deemed to be a dominant traffic type, and require quality of service (QoS) support. However, in the current IEEE 802.15.3 standard for MAC (media access control) of high-rate WPANs, the implementation details of some key issues such as scheduling and QoS provisioning have not been addressed. In this paper, we first propose a Markov decision process (MDP) model for optimal scheduling for video flows in high-rate WPANs. Using this model, we also propose a scheduler that incorporates compact state space representation, function approximation, and reinforcement learning (RL). Simulation results show that our proposed RL scheduler achieves nearly optimal performance and performs better than F-SRPT, EDD+SRPT, and PAP scheduling algorithms in terms of a lower decoding failure rate.