Dissertation
Sarah Osentoski, Action-Based Representation Discovery in Markov Decision Processes, PhD thesis, Computer Science, University of Massachusetts Amherst, 2009Publications
Sarah Osentoski, Graylin Jay, Christopher Crick, Benjamin Pitzer, Charles DuHadway, and Odest Chadwicke Jenkins, Robots as Web Services: Reproducible Experimentation and Application Development Using rosjs, Proceedings of 2011 IEEE International Conference on Robotics and Automation (ICRA 2011), to appear
George Konidaris, Sarah Osentoski, and Philip Thomas, Value Function Approximation in Reinforcement Leanring using the Fourier Basis, Proceedings of the Twenty-Fifth Conference on Artificial Intelligence, to appear
Christopher Crick, Sarah Osentoski, Graylin Jay, and Odest Chadwicke Jenkins, Human and Robot Perception in Large-scale Learning from Demonstration, Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2011, to appear
Sarah Osentoski and Sridhar Mahadevan, Basis Function Construction for Hierarchical Reinforcement Learning, Nineth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Toronto, Canada, 2010
Sarah Osentoski, Christopher Crick, Graylin Jay, and Odest Chadwicke Jenkins, Crowdsourcing for closed loop control, NIPS Workshop on Computational Social Science and the Wisdom of Crowds, 2010.
Jesse Butterfield, Sarah Osentoski, Graylin Jay, and Odest Chadwicke Jenkins, Learning from Demonstration using a Multi-valued Function Regressor for Time-series Data, Tenth IEEE-RAS International Conference on Humanoid Robots (Humanoids), Nashville, Tennesse, 2010
Sarah Osentoski, Graylin Jay, Christopher Crick, and Odest Chadwick Jenkins, Brown ROS Package: Reproducibility for Shared Experimentation and Learning from Demonstration (extended abstract), AAAI-10 Robot Workshop, Atlanta, Georgia, 2010
Sarah Osentoski and Sridhar Mahadevan, Basis Function Construction for Hierarchical Reinforcement Learning, Workshop on Abstraction in Reinforcement Learning, Joint workshop at ICML, UAI, and COLT, Montreal, Canada, June 2009.
George Konidaris and Sarah Osentoski, Value Function Approximation using the Fourier Basis (extended abstract), Multidisciplinary Symposium on Reinforcement Learning, Montreal, Canada, June 2009.
George Konidaris and Sarah Osentoski, Value Function Approximation in Reinforcement Learning using the Fourier Basis, Technical Report UM-CS-2008-19, Department of Computer Science, University of Massachusetts Amherst, June 2008.
Sridhar Mahadevan, Sarah Osentoski, Jeff Johns, Kimberly Ferguson, and Chang Wang, Learning to Plan Using Harmonic Analysis of Diffusion Models, International Conference on Automated Planning and Scheduling (ICAPS), September 22-26, 2007, Providence RI.
Sarah Osentoski and Sridhar Mahadevan, Learning State-Action Basis Functions for Hierarchical MDPs, International Conference Machine Learning (ICML), June 20-24, 2007, Corvallis Oregon.
Jeff Johns, Sarah Osentoski, and Sridhar Mahadevan, Representation Discovery in Planning using Harmonic Analysis, Proceedings of the AAAI Fall Symposium on Comutational Approaches to Representation Change During Learning and Development, Washington, D.C., 2007.
Sridhar Mahadevan, Mauro Maggioni, Kimberly Ferguson, and Sarah Osentoski, Learning Representation and Control in Continuous Markov Decision Processes, AAAI, 2006, Boston, July.
Sarah Osentoski, Victoria Manfredi, and Sridhar Mahadevan, Learning Hierarchical Models of Activity , IEEE/RSJ International Conference on Robots and Systems (IROS), 2004.
P. E. Rybski, A. Larson, A. Schoolcraft, S. Osentoski and M. Gini, Evaluation of Control Strategies for Multi-Robot Search and Retrieval, Proceedings of The 7th International Conference on Intelligent Autonomous Systems (IAS-7), pp. 281-288, Marina del Rey, CA, March 2002.