Corpus ID: 235829188

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

@article{Huang2021GoingBL,
  title={Going Beyond Linear RL: Sample Efficient Neural Function Approximation},
  author={Baihe Huang and Kaixuan Huang and Sham M. Kakade and Jason D. Lee and Qi Lei and Runzhe Wang and Jiaqi Yang},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.06466}
}
  • Baihe Huang, Kaixuan Huang, +4 authors Jiaqi Yang
  • Published 2021
  • Computer Science, Mathematics
  • ArXiv
Deep Reinforcement Learning (RL) powered by neural net approximation of the Q function has had enormous empirical success. While the theory of RL has traditionally focused on linear function approximation (or eluder dimension) approaches, little is known about nonlinear RL with neural net approximations of the Q functions. This is the focus of this work, where we study function approximation with two-layer neural networks (considering both ReLU and polynomial activation functions). Our first… Expand

Figures and Tables from this paper