An adaptive work distribution mechanism based on reinforcement learning.
Zhengxing HuangWil M. P. van der AalstXudong LuHuilong DuanPublished in: Expert Syst. Appl. (2010)
Keyphrases
- monte carlo
- reinforcement learning
- temporal difference
- function approximation
- temporal difference learning
- uniformly distributed
- probability distribution
- reinforcement learning algorithms
- machine learning
- adaptive learning
- model free
- state space
- multi agent
- mechanism design
- data distribution
- database
- density function
- normal distribution
- real time
- robot control
- search engine
- spatial distribution
- optimal control
- training data
- random variables
- supervised learning