Logarithmic Regret for Reinforcement Learning with Linear Function Approximation.
Jiafan HeDongruo ZhouQuanquan GuPublished in: ICML (2021)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- regret bounds
- temporal difference
- temporal difference learning
- model free
- mountain car
- learning tasks
- radial basis function
- tile coding
- state space
- reinforcement learning algorithms
- learning algorithm
- state action space
- reward function
- multi agent
- td learning
- optimal control
- data mining
- supervised learning
- neural network
- learning problems
- pattern recognition
- actor critic