Reinforcement Learning in Low-Rank MDPs with Density Features.
Audrey HuangJinglin ChenNan JiangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- low rank
- markov decision processes
- convex optimization
- state space
- matrix factorization
- linear combination
- missing data
- rank minimization
- robust principal component analysis
- data mining
- low rank matrix
- matrix completion
- function approximation
- optimal policy
- small number
- semi supervised
- feature space
- learning algorithm
- high order
- singular value decomposition
- high dimensional data
- image restoration
- model free
- feature vectors
- trace norm
- feature extraction