Reinforcement Learning in Low-rank MDPs with Density Features.
Audrey HuangJinglin ChenNan JiangPublished in: ICML (2023)
Keyphrases
- low rank
- reinforcement learning
- markov decision processes
- missing data
- state space
- convex optimization
- markov decision process
- kernel matrix
- feature vectors
- high dimensional data
- matrix factorization
- singular value decomposition
- rank minimization
- function approximation
- feature extraction
- optimal policy
- matrix decomposition
- linear combination
- semi supervised
- model free
- reinforcement learning algorithms
- machine learning
- matrix completion
- data mining