Going Beyond Linear RL: Sample Efficient Neural Function Approximation.
Baihe HuangKaixuan HuangSham M. KakadeJason D. LeeQi LeiRunzhe WangJiaqi YangPublished in: NeurIPS (2021)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- tile coding
- model free
- radial basis function
- learning tasks
- neural network
- reinforcement learning algorithms
- temporal difference learning
- temporal difference methods
- state space
- machine learning
- learning algorithm
- markov decision processes
- actor critic