— Allowing robots to communicate naturally with humans is a major goal for social robotics. Most approaches have focused on building high-level probabilistic cognitive models. Ho...
Eric Meisner, Sanmay Das, Volkan Isler, Jeff Trink...
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....
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...