You are currently offline. Some features of the site may not work correctly.

Corpus ID: 222208635

Learning the Linear Quadratic Regulator from Nonlinear Observations

@article{Mhammedi2020LearningTL,
title={Learning the Linear Quadratic Regulator from Nonlinear Observations},
author={Zakaria Mhammedi and Dylan J. Foster and Max Simchowitz and Dipendra Misra and W. Sun and A. Krishnamurthy and A. Rakhlin and J. Langford},
journal={ArXiv},
year={2020},
volume={abs/2010.03799}
}

We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional continuous latent state with linear dynamics and quadratic costs, but the agent operates on high-dimensional, nonlinear observations such as images from a camera. To enable sample-efficient learning, we assume that the learner has access to a class of decoder functions (e.g., neural networks) that is flexible enough to… Expand