Learning the Linear Quadratic Regulator from Nonlinear Observations

NIPS 2020, 2020.

Cited by: 0|Views35
EI
Weibo:
We introduce a new problem setting for continuous control called the LQR with Rich Observations, or rich observation linear quadratic regulator

Abstract:

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....More

Code:

Data:

Your rating :
0

 

Tags
Comments