Least Squares Policy Evaluation Algorithms with Linear Function Approximation.
Angelia NedicDimitri P. BertsekasPublished in: Discret. Event Dyn. Syst. (2003)
Keyphrases
- policy evaluation
- least squares
- function approximation
- temporal difference
- model free
- reinforcement learning
- td learning
- policy iteration
- monte carlo
- temporal difference learning algorithms
- semi parametric
- function approximators
- linear model
- markov decision processes
- optical flow
- partially observable markov decision processes
- dynamic programming
- evaluation function
- variance reduction
- neural network
- learning tasks
- radial basis function
- optimal policy