— 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...
We address the problem of optimally controlling stochastic environments that are partially observable. The standard method for tackling such problems is to define and solve a Part...