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