Overcoming the Long Horizon Barrier for Sample-Efficient Reinforcement Learning with Latent Low-Rank Structure.
Tyler SamYudong ChenChristina Lee YuPublished in: SIGMETRICS (Abstracts) (2023)
Keyphrases
- low rank
- reinforcement learning
- missing data
- convex optimization
- matrix completion
- matrix factorization
- singular value decomposition
- function approximation
- rank minimization
- kernel matrix
- low rank matrix
- linear combination
- neural network
- trace norm
- low rank matrices
- high dimensional data
- semi supervised
- probabilistic model
- matrix decomposition