Sciweavers

7 search results - page 2 / 2
» Nonlinear programming in approximate dynamic programming - b...
Sort
View
NIPS
1996
13 years 7 months ago
Multidimensional Triangulation and Interpolation for Reinforcement Learning
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
Scott Davies
BROADNETS
2005
IEEE
13 years 12 months ago
Multi-rate throughput optimization for wireless local area network anomaly problem
— Due to varying wireless channel conditions, the IEEE 802.11 wireless local area network (WLAN) standard supports multiple modulation types to accommodate the tradeoff between d...
Yu-Liang Kuo, Kun-Wei Lai, Frank Yeong-Sung Lin, Y...