Sanmit Narvekar

sanmit at cs dot utexas dot edu
Office: GDC 3.424E
Sanmit's Picture

About Me

I'm a PhD student in the Department of Computer Science at the University of Texas at Austin, advised by Peter Stone. My research is on curriculum learning -- the automated design of a sequence of tasks that enable autonomous agents to learn faster or better. I'm also a member of the UT Austin Villa Standard Platform League team, where I work primarily on the vision system.

I received my BS in computer science from California State University, Los Angeles, where I worked on using probabilistic automata (e.g. HMMs, etc.) for anomaly detection in computer agents with Professor Valentino Crespi. I also worked part time at the Jet Propulsion Laboratory on using multispectral and synthetic aperture radar data to detect natural disasters such as flooding, etc., and on telemetry processing.

Teaching

Fall 2015: TA for CS 344M: Autonomous Multiagent Systems
Fall 2016: TA for CS 394R: Reinforcement Learning: Theory and Practice

Publications

Refereed Conferences

Sanmit Narvekar, Jivko Sinapov, and Peter Stone. Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, August 19-25, 2017. [pdf] [bib] [slides]

Sanmit Narvekar, Jivko Sinapov, Matteo Leonetti, and Peter Stone. Source Task Creation for Curriculum Learning. In Proceedings of the 15th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2016), Singapore, May 9-13, 2016. [pdf] [bib] [slides]

Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti, and Peter Stone. Learning Inter-Task Transferability in the Absence of Target Task Samples. In Proceedings of the 14th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2015), Istanbul, Turkey, May 4-8, 2015. [pdf] [bib]

Refereed Workshops and Symposia

Sanmit Narvekar, Jivko Sinapov, and Peter Stone. Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning. In 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), Ann Arbor, Michigan, June 11-14, 2017. This paper is superceded by the IJCAI 2017 paper with the same name.

Book Chapters

Jacob Menashe, Josh Kelle, Katie Genter, Josiah Hanna, Elad Liebman, Sanmit Narvekar, Ruohan Zhang, and Peter Stone. Fast and Precise Black and White Ball Detection for RoboCup Soccer. In RoboCup 2017: Robot Soccer World Cup XXI, Lecture Notes in Artificial Intelligence, Springer, 2017. [pdf] [bib]

Magazines and Other

Katie Genter, Patrick MacAlpine, Jacob Menashe, Josiah Hanna, Elad Liebman, Sanmit Narvekar, Rouhan Zhang, and Peter Stone. UT Austin Villa: Project-Driven Research in AI and Robotics. In IEEE Intelligent Systems, Expert Opinion, March 2016.