Gaussian Based Non-linear Function Approximation for Reinforcement Learning.
Abbas HaiderGlenn I. HaweHui WangBryan W. ScotneyPublished in: SN Comput. Sci. (2021)
Keyphrases
- function approximation
- reinforcement learning
- mountain car
- function approximators
- state action space
- temporal difference
- temporal difference learning
- model free
- tile coding
- radial basis function
- temporal difference learning algorithms
- learning tasks
- state space
- reinforcement learning algorithms
- td learning
- optimal policy
- machine learning
- policy evaluation
- neural network
- continuous state
- learning process
- learning algorithm