The goal of this workshop is to bring researchers from multiple disciplines together who are in one way or another affected by the gap between perception, action and communication that typically exists for data-driven interactive systems or robots. We aim to provide a forum for interdisciplinary discussion that allows researchers to look at their work from new perspectives that go beyond their core community and potentially develop new interdisciplinary collaborations driven by machine learning. A multidisciplinary viewpoint is important to develop agents with a holistic perspective of the world. This is also vital for the design of agents that solve large-scale and complex real-world problems in a principled way. Machine learning will stand at the core of the workshop as a common interest across researchers.