Model-free Representation Learning and Exploration in Low-rank MDPs.
Aditya ModiJinglin ChenAkshay KrishnamurthyNan JiangAlekh AgarwalPublished in: CoRR (2021)
Keyphrases
- training set
- reinforcement learning
- active learning
- supervised learning
- low rank
- model free
- data sets
- learning process
- markov decision processes
- learning algorithm
- average reward
- policy iteration
- reinforcement learning algorithms
- linear combination
- action selection
- singular value decomposition
- learning tasks
- convex optimization
- matrix factorization
- matrix completion
- function approximation
- missing data
- low dimensional
- linear programming
- data analysis
- neural network