In this paper we study instruction following in text-based games and propose an approach that advances theprevious stateoftheart.

Owing to their stability and convergence speed, extragradient methods have become astaple forsolving large-scale saddle-point problems inmachine learning.

Hence, GPN brings a small computational overhead for uncertainty estimation during inference but is significantly faster than ensemble or dropout approaches.

The emergence of the Internet-of-Things (IoT) sheds light on applying the machine teaching (MT) algorithms for online personalized education on home devices.