My research interests lie at the intersection of the fields of machine learning, cognitive neuroscience, and developmental robotics. More specifically, I am interested in the design of artificial systems that exhibit life-long, motivated, cumulative learning of increasingly complex perceptual and behavioral representations. Such representations, I believe, must be learned in a developmental setting as they are in humans and animals, and so computational architectures inspired by principles of neural and behavioral development in biological systems interest me greatly.
My doctoral research under my advisor, Professor Andrew Barto, involved the development of algorithms for intrinsically motivated learning of hierarchies of skills in artificial agents. We used reinforcement learning as a formalism to explore ways of modeling intrinsically motivated behavior in humans and animals; i.e., behavior that is rewarding for its own sake, rather than because it solves a specific task.
As an undergraduate, I was also involved in research with Professor John Moore and Robert Polewan of the UMass Department of Neuroscience and Behavior. We developed a human eyeblink conditioning paradigm (the Cartesian Reflex Project) for studying the effects of different stimuli (e.g., faces vs. geometric shapes) on cognitive processing time in traditional classical conditioning tasks with voluntary unconditioned responses. My primary contribution to this endeavor was the development of the hardware/software interface and protocol design software used in the paradigm.
- Vigorito, C.M. (2016). Intrinsically Motivated Exploration in Hierarchical Reinforcement Learning. PhD Thesis, School of Computer Science, University of Massachusetts Amherst, February 2016. [pdf][BibTeX]
- Barto, A.G., Konidaris, G.D., and Vigorito, C.M. (2013). Behavioral Hierarchy: Exploration and Representation. Computational and Robotic Models of the Hierarchical Organization of Behavior, October 2013. [pdf][BibTeX]
- Vigorito, C.M. and Barto, A.G. (2010). Intrinsically Motivated Hierarchical Skill Learning in Structured Environments. IEEE Transactions on Autonomous Mental Development (TAMD). Volume 2, Issue 2. [pdf][BibTeX]
- Vigorito, C.M. and Barto, A.G. (2009). Incremental Structure Learning in Factored MDPs with Continuous States and Actions. Technical Report UM-CS-2009-029, Department of Computer Science, University of Massachusetts Amherst. [pdf] [BibTeX]
- Vigorito, C.M. (2009). Temporal-Difference Networks for Dynamical Systems with Continuous Observations and Actions. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI). Montreal, Quebec, CA. [pdf] [poster] [BibTeX]
- Vigorito, C.M. and Barto, A.G. (2008). Autonomous Hierarchical Skill Acquisition in Factored MDPs. Proceedings of The Fourteenth Yale Workshop on Adaptive and Learning Systems. New Haven, CT. [pdf] [BibTeX]
- Vigorito, C.M. and Barto, A.G. (2008). Hierarchical Representations of Behavior for Efficient Creative Search. AAAI Spring Symposium on Creative Intelligent Systems, Palo Alto, CA. [pdf] [poster] [BibTeX]
- Vigorito, C.M., Ganesan, D., and Barto, A.G. (2007). Adaptive Control of Duty-Cycling in Energy-Harvesting Wireless Sensor Networks, Proceedings of the Fourth Annual IEEE Communications Society Conference on Sensor, Mesh, and Ad Hoc Communications and Networks (SECON), San Diego, CA. (Best Paper Award) [pdf] [BibTeX]
- Vigorito, C. (2007). Distributed Path Planning for Mobile Robots using a Swarm of Interacting Reinforcement Learners. Proceedings of the Sixth Annual International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Honolulu, HI. [pdf] [slides] [BibTeX]
- Polewan, R., Vigorito, C.M., Nason, C., Block, R., and Moore, J.W. (2006). A Cartesian Reflex Assessment of Face Processing. Behavioral and Cognitive Neuroscience Reviews, Vol. 5, No. 1, pp. 3-23. [pdf] [BibTeX]