Reinforcement Learning for Matrix Computations: PageRank as an Example.
Vivek S. BorkarAdwaitvedant S. MathkarPublished in: ICDCIT (2014)
Keyphrases
- reinforcement learning
- state space
- random walk
- linear algebra
- matrix multiplication
- markov decision processes
- reinforcement learning algorithms
- multi agent
- singular value decomposition
- function approximation
- temporal difference
- link analysis
- learning process
- web search
- google search engine
- function approximators
- model free
- low rank
- ranking algorithm
- optimal policy
- machine learning
- learning algorithm
- temporal difference learning
- coefficient matrix
- policy search
- neural network