Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation.
Jiayi HuangHan ZhongLiwei WangLin F. YangPublished in: CoRR (2023)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- temporal difference learning
- special case
- model free
- function approximators
- learning tasks
- radial basis function
- reinforcement learning algorithms
- markov decision processes
- policy search
- decision trees
- supervised learning
- transfer learning
- td learning