Efficient Model-Free Exploration in Low-Rank MDPs.
Zakaria MhammediAdam BlockDylan J. FosterAlexander RakhlinPublished in: CoRR (2023)
Keyphrases
- low rank
- model free
- reinforcement learning
- policy iteration
- markov decision processes
- convex optimization
- linear combination
- high dimensional data
- reinforcement learning algorithms
- function approximation
- policy evaluation
- average reward
- matrix factorization
- singular value decomposition
- semi supervised
- missing data
- matrix completion
- rank minimization
- low rank matrix
- neural network
- trace norm
- pattern recognition