Representation Learning for Online and Offline RL in Low-rank MDPs.
Masatoshi UeharaXuezhou ZhangWen SunPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- low rank
- learning algorithm
- markov decision processes
- missing data
- learning process
- learning problems
- supervised learning
- state space
- high order
- neural network
- convex optimization
- decision trees
- group sparsity
- function approximation
- image representation
- model free
- learning tasks
- optimal policy
- linear programming
- nearest neighbor
- active learning
- pattern recognition
- data mining