The Importance of Sampling inMeta-Reinforcement Learning

Abstract

We interpret meta-reinforcement learning as the problem of learning how to quickly find a good sampling distribution in a new environment. This interpretation leads to the development of two new meta-reinforcement learning algorithms: E-MAML and E-$\text{RL}^2$. Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning. Further results are presented on a set of maze environments. We show E-MAML and E-$\text{RL}^2$ deliver better performance than baseline algorithms on both tasks.

Cite

Text

Stadie et al. "The Importance of Sampling inMeta-Reinforcement Learning." Neural Information Processing Systems, 2018.

Markdown

[Stadie et al. "The Importance of Sampling inMeta-Reinforcement Learning." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/stadie2018neurips-importance/)

BibTeX

@inproceedings{stadie2018neurips-importance,
  title     = {{The Importance of Sampling inMeta-Reinforcement Learning}},
  author    = {Stadie, Bradly and Yang, Ge and Houthooft, Rein and Chen, Peter and Duan, Yan and Wu, Yuhuai and Abbeel, Pieter and Sutskever, Ilya},
  booktitle = {Neural Information Processing Systems},
  year      = {2018},
  pages     = {9280-9290},
  url       = {https://mlanthology.org/neurips/2018/stadie2018neurips-importance/}
}