Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation.
Yu ChenYihan DuPihe HuSiwei WangDesheng WuLongbo HuangPublished in: CoRR (2023)
Keyphrases
- function approximation
- reinforcement learning
- tile coding
- temporal difference
- function approximators
- mountain car
- state action space
- learning tasks
- temporal difference learning
- radial basis function
- temporal difference learning algorithms
- model free
- reinforcement learning algorithms
- learning process
- policy search
- data points
- temporal difference methods
- machine learning
- neural network