About Me

I am a doctoral student in Computer Science at UMass, where I work with Andrew Barto and Rod Grupen. I study a subfield of Artificial Intelligence called Developmental Robotics; for more about my research, see below. I graduated from Swarthmore College in 2003, and from the Illinois Mathematics and Science Academy in 1999--both were amazing, wonderful, formative places.

Research Interests

Developmental robotics and intrinsically motivated reinforcement learning. Artificial intelligence, robotics, machine learning, development, artificial life, evolutionary computation, self-organization, complex adaptive systems, agent-based modeling.

Through my research I seek to understand the computational principles of systems that display continual, open-ended, endogenous adaptation, by synthesizing similarly autonomous and adaptive artificial systems.

My driving interest is in discovering representations and algorithms for constructive, grounded, long-term, domain-general cognitive and motor development in robots. Toward this end, I am studying principled, endogenous mechanisms for structuring and organizing developmental progression. My focus is on one broad classes of such mechanisms: motivation. Internal motivation systems take the place of (or augment) the external supervisory signals ubiquitous in traditional machine learning, providing to learning mechanisms an internally-generated reward signal. A dynamic motivational system biases the attention of the learner on developmentally appropriate tasks, and is essential to driving the continual bootstrapping of increasingly sophisticated learning. My goal is to identify a compact set of rewarding conditions that give rise to an extended, open-ended progression of learning, leading to a hierarchy of learned skills from uniform motivational criteria. I am currently developing a system motivated by competence progress, that is, improvement in the agent's skill policies. I am eager to prove the utility of a developmental approach to endowing real robots with useful abilities.

More generally, I am interested in applying artificial intelligence and machine learning to the challenges of programming robots. I have a sustained, albeit neglected, secondary interest in complex systems, self-organization, and evolutionary computation; this interest is most at home in the multidisciplinary fields of Artificial Life and Complexity Science.


  • Andrew Stout and Andrew Barto - Competence Progress Intrinsic Motivation. Proceedings of the International Conference on Development and Learning, 2010. [pdf]
  • Andrew Stout, George Konidaris, and Andrew Barto - Intrinsically Motivated Reinforcement Learning: A Promising Framework For Developmental Robot Learning. Proceedings of the AAAI Spring Symposium on Developmental Robotics, 2005. [pdf]
  • Andrew Stout and Lee Spector - Validation of Evolutionary Activity Metrics for Long-Term Evolutionary Dynamics. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), 2005. [pdf]
  • Julie Corder, Oliver Hsu, Andrew Stout, and Bruce Maxwell - A Modular Software Architecture for Heterogeneous Robot Tasks. Proceedings of the AAAI Workshop on Mobile Robotics, 2002.