A Cross Entropy based Stochastic Approximation Algorithm for Reinforcement Learning with Linear Function Approximation.
Ajin George JosephShalabh BhatnagarPublished in: CoRR (2016)
Keyphrases
- stochastic approximation
- function approximation
- reinforcement learning
- function approximators
- model free
- temporal difference learning
- dynamic programming
- learning algorithm
- temporal difference learning algorithms
- monte carlo
- policy iteration
- linear programming
- state space
- neural network
- actor critic
- policy evaluation
- objective function
- optimal solution
- single agent
- reinforcement learning algorithms
- temporal difference
- search space
- multi agent
- radial basis function
- support vector machine svm
- td learning
- least squares