Low-rank State-action Value-function Approximation.
Sergio RozadaVictor TenorioAntonio G. MarquesPublished in: CoRR (2021)
Keyphrases
- state action
- low rank
- kernel matrix
- evaluation function
- missing data
- reinforcement learning
- matrix factorization
- semidefinite programming
- convex optimization
- linear combination
- semi supervised
- singular value decomposition
- high dimensional data
- high order
- state transitions
- markov decision process
- collaborative filtering
- stochastic games
- reward function
- pairwise
- fixed point
- dimensionality reduction
- least squares
- state space
- high dimensional
- action space