In this work, we present an approach to identify sub-tasks within a
demo...
Modern day computer games have extremely large state and action spaces. ...
We propose a framework that learns to execute natural language instructi...
Policy specification is a process by which a human can initialize a robo...
Natural language object retrieval is a highly useful yet challenging tas...
We develop a system to disambiguate objects based on simple physical
des...
An agent with an inaccurate model of its environment faces a difficult
c...
Robots operating alongside humans in diverse, stochastic environments mu...
Humans can ground natural language commands to tasks at both abstract an...