Matteo Leonetti
Postdoctoral Alumni
Matteo's research is about the application of AI to robotics, in particular about decision making. His work is focused on mitigating the uncertainty on knowledge representations in autonomous robots, and the consequent flimsy behavior, through reinforcement learning. He is in general interested in how the rationality of automated reasoning can come to terms with the wild attitude towards exploration of most machine learning.
Homepage:
http://www.cs.utexas.edu/~matteo/
Publications
Automatic Curriculum Graph Generation for Reinforcement Learning Agents 2017
Maxwell Svetlik, Matteo Leonetti, Jivko Sinapov, Rishi Shah, Nick Walker, and Peter Stone, In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, CA, February 2017.
BWIBots: A platform for bridging the gap between AI and human--robot interaction research 2017
Piyush Khandelwal, Shiqi Zhang, Jivko Sinapov, Matteo Leonetti, Jesse Thomason, Fangkai Yang, Ilaria Gori, Maxwell Svetlik, Priyanka Khante, Vladimir Lifschitz, J. K. Aggarwal, Raymond Mooney, and Peter Stone, The International Journal of Robotics Research (2017).
A synthesis of automated planning and reinforcement learning for efficient, robust decision-making 2016
Matteo Leonetti, Luca Iocchi, and Peter Stone, Artificial Intelligence, Vol. 241 (2016), pp. 103 - 130.
Source Task Creation for Curriculum Learning 2016
Sanmit Narvekar, Jivko Sinapov, Matteo Leonetti, and Peter Stone, In Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), Singapore, May 2016.
State Aggregation through Reasoning in Answer Set Programming 2016
Ginevra Gaudioso, Matteo Leonetti, and Peter Stone, In Proceedings of the IJCAI Workshop on Autonomous Mobile Service Robots (WSR 16), New York City, NY, USA, July 2016.
Learning Inter-Task Transferability in the Absence of Target Task Samples 2015
Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti, and Peter Stone, In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Istanbul, Turkey, May 2015.
Labs
Formerly affiliated with Learning Agents