We introduce the controlled predictive linearGaussian model (cPLG), a model that uses predictive state to model discrete-time dynamical systems with real-valued observations and v...
—Robotic systems need to be able to plan control actions that are robust to the inherent uncertainty in the real world. This uncertainty arises due to uncertain state estimation,...
Lars Blackmore, Masahiro Ono, Askar Bektassov, Bri...
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Predictive state representations (PSRs) use predictions of a set of tests to represent the state of controlled dynamical systems. One reason why this representation is exciting as...
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....