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

Tables from this paper

References

SHOWING 1-10 OF 53 REFERENCES
Predictive Coding for Locally-Linear Control
  • 2
  • Highly Influential
  • PDF
Extracting Latent State Representations with Linear Dynamics from Rich Observations
  • 1
  • PDF
Robust Locally-Linear Controllable Embedding
  • 41
  • Highly Influential
  • PDF
Improper Learning for Non-Stochastic Control
  • 30
  • PDF
Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control
  • 9
  • Highly Influential
  • PDF
Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems
  • 7
  • PDF
Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems
  • 19
  • PDF
Learning Linear Dynamical Systems with Semi-Parametric Least Squares
  • 42
  • PDF
Learning Latent Dynamics for Planning from Pixels
  • 336
  • Highly Influential
  • PDF
...
1
2
3
4
5
...