Multi-User Reinforcement Learning with Low Rank Rewards.
Naman AgarwalPrateek JainSuhas S. KowshikDheeraj NagarajPraneeth NetrapalliPublished in: CoRR (2022)
Keyphrases
- multi user
- low rank
- reinforcement learning
- linear combination
- missing data
- convex optimization
- matrix factorization
- markov decision processes
- virtual environment
- virtual world
- singular value decomposition
- low rank matrix
- function approximation
- semi supervised
- single user
- user interface
- rank minimization
- multi granularity
- high dimensional data
- matrix completion
- multiple users
- matrix decomposition
- augmented reality
- trace norm
- minimization problems
- kernel matrix
- high order
- state space
- low rank matrices
- machine learning
- model free
- learning algorithm
- singular values
- reinforcement learning algorithms
- optimal policy
- reward function
- temporal difference
- transfer learning
- robust principal component analysis
- human computer interaction
- higher order
- learning problems
- learning process
- high dimensional
- data analysis
- pattern recognition