An Efficient, Expressive and Local Minima-Free Method for Learning Controlled Dynamical Systems

THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, pp. 3191-3198, 2018.

Cited by: 3|Views49
EI

Abstract:

We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations. Based on this framework, we propose Predictive State Representation with Random Fourier Features (RFF-PSR). A key property in RFF-PSRs is that the state estim...More

Code:

Data:

Your rating :
0

 

Tags
Comments