SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation.
Bo DaiAlbert ShawLihong LiLin XiaoNiao HeZhen LiuJianshu ChenLe SongPublished in: ICML (2018)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- tile coding
- mountain car
- temporal difference learning
- function approximators
- state action space
- state space
- learning tasks
- radial basis function
- model free
- temporal difference learning algorithms
- reinforcement learning algorithms
- optimal policy
- learning process
- artificial neural networks
- multi agent
- machine learning
- monte carlo
- reinforcement learning methods
- continuous state
- td learning
- neural network