Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback.
Yu ChenYihan DuPihe HuSiwei WangDesheng WuLongbo HuangPublished in: ICLR (2024)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- model free
- temporal difference learning
- tile coding
- function approximators
- mountain car
- temporal difference learning algorithms
- radial basis function
- reinforcement learning algorithms
- state action space
- td learning
- multi agent
- learning tasks
- markov decision processes
- relevance feedback
- learning process
- reinforcement learning methods
- continuous state
- machine learning
- temporal difference methods
- neural network