A unified framework for linear function approximation of value functions in stochastic control.
Matilde Sánchez FernándezSergio Valcarcel MacuaSantiago ZazoPublished in: EUSIPCO (2013)
Keyphrases
- function approximation
- temporal difference learning algorithms
- stochastic control
- reinforcement learning
- function approximators
- learning tasks
- temporal difference
- radial basis function
- control problems
- queueing systems
- temporal difference learning
- model free
- rl algorithms
- optimal control
- operations management
- feature selection
- reinforcement learning algorithms
- kernel methods