Due to the recent progress in Deep Neural Networks, Reinforcement Learning (RL) has
become one of the most important and useful technology. It is a learning method where a …

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the
compositional, relational, and hierarchical structure of the world, and learn to transfer it to the …

To interact with humans in the world, agents need to understand the diverse types of
language that people use, relate them to the visual world, and act based on them. While …

In this paper, we consider the task of learning control policies for text-based games. In these
games, all interactions in the virtual world are through text and the underlying state is not …

This paper presents a novel approach to learning to solve simple arithmetic word problems.
Our system, ARIS, analyzes each of the sentences in the problem statement to identify the …

Suppose we want to build a system that answers a natural language question by
representing its semantics as a logical forxm and computing the answer given a structured …

Deep neural networks have achieved impressive supervised classification performance in
many tasks including image recognition, speech recognition, and sequence to sequence …

High sample complexity has long been a challenge for RL. On the other hand, humans learn
to perform tasks not only from interaction or demonstrations, but also by reading …

This paper introduces GEOS, the first automated system to solve unaltered SAT geometry
questions by combining text understanding and diagram interpretation. We model the …

Task semantics can be expressed by a set of input-output examples or a piece of textual
instruction. Conventional machine learning approaches for natural language processing …