Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition.
Yash ChandakShantanu ThakoorZhaohan Daniel GuoYunhao TangRémi MunosWill DabneyDiana L. BorsaPublished in: ICML (2023)
Keyphrases
- singular value decomposition
- reinforcement learning
- least squares
- action selection
- reconstruction error
- singular values
- function approximation
- dimension reduction
- dimensionality reduction
- low rank
- principal component analysis
- latent semantic analysis
- latent semantic indexing
- temporal difference
- singular vectors
- function approximators
- low rank approximation
- low rank matrix
- data matrix
- neural network
- feature space
- machine learning