Provably Efficient CVaR RL in Low-rank MDPs.
Yulai ZhaoWenhao ZhanXiaoyan HuHo-fung LeungFarzan FarniaWen SunJason D. LeePublished in: CoRR (2023)
Keyphrases
- low rank
- reinforcement learning
- markov decision processes
- matrix factorization
- convex optimization
- matrix completion
- state space
- singular value decomposition
- trace norm
- rank minimization
- kernel matrix
- semi supervised
- missing data
- low rank matrix
- neural network
- markov decision process
- minimization problems
- robust principal component analysis
- non rigid structure from motion
- high order
- optimal policy
- linear combination
- low rank matrices
- total variation
- reinforcement learning algorithms
- model free
- high dimensional data
- higher order
- pairwise
- data analysis
- learning algorithm