Adapting the Function Approximation Architecture in Online Reinforcement Learning.
John D. MartinJoseph ModayilPublished in: CoRR (2021)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- temporal difference learning
- function approximators
- tile coding
- mountain car
- model free
- temporal difference learning algorithms
- state action space
- reinforcement learning algorithms
- radial basis function
- learning tasks
- td learning
- learning capabilities
- state space
- neural network
- learning algorithm
- transfer learning
- optimal policy
- policy iteration
- supervised learning
- multi agent
- feature selection
- exploration exploitation tradeoff