Offline Reinforcement Learning with Differentiable Function Approximation Is Provably Efficient

Abstract

Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-Of-The-Art algorithms usually leverage powerful function approximators (e.g. neural networks) to alleviate the sample complexity hurdle for better empirical performances. Despite the successes, a more systematic under- standing of the statistical complexity for function approximation remains lacking. Towards bridging the gap, we take a step by considering offline reinforcement learning with differentiable function class approximation (DFA). This function class naturally incorporates a wide range of models with nonlinear/nonconvex structures. We show offline RL with differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning (PFQL) algorithm, and our results provide the theoretical basis for understanding a variety of practical heuristics that rely on Fitted Q-Iteration style design. In addition, we further im- prove our guarantee with a tighter instance-dependent characterization. We hope our work could draw interest in studying reinforcement learning with differentiable function approximation beyond the scope of current research.

Cite

Text

Yin et al. "Offline Reinforcement Learning with Differentiable Function Approximation Is Provably Efficient." International Conference on Learning Representations, 2023.

Markdown

[Yin et al. "Offline Reinforcement Learning with Differentiable Function Approximation Is Provably Efficient." International Conference on Learning Representations, 2023.](https://mlanthology.org/iclr/2023/yin2023iclr-offline/)

BibTeX

@inproceedings{yin2023iclr-offline,
  title     = {{Offline Reinforcement Learning with Differentiable Function Approximation Is Provably Efficient}},
  author    = {Yin, Ming and Wang, Mengdi and Wang, Yu-Xiang},
  booktitle = {International Conference on Learning Representations},
  year      = {2023},
  url       = {https://mlanthology.org/iclr/2023/yin2023iclr-offline/}
}