Scott Niekum
Faculty
I am an Assistant Professor and the director of the Personal Autonomous Robotics Lab (PeARL) in the Department of Computer Science at the University of Texas at Austin. I am also a core faculty member in the interdepartmental robotics group here at UT. The goal of my research is to enable personal robots to be deployed in the home and workplace with minimal intervention by robotics experts. In settings such as these, robots do not operate in isolation, but have continual interactions with people and objects in the world. With this in mind, we focus on developing algorithms to solve problems that robot learners encounter in real-world interactive settings. Thus, our work draws roughly equally from both machine learning and robotics, including topics such as learning from demonstration, manipulation, human-robot interaction, interactive perception, and reinforcement learning. Prior to joining UT Austin, I was a postdoctoral research fellow at the Carnegie Mellon Robotics Institute, working with Chris Atkeson. I received my PhD in September 2013 from the Department of Computer Science at the University of Massachusetts Amherst, working under the supervision of Andrew Barto.
Homepage:
http://www.cs.utexas.edu/~sniekum/
Publications
The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications 2023
Serena Booth, W Bradley Knox, Julie Shah, Scott Niekum, Peter Stone, and Alessandro Allievi, In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), Washington, D.C., February 2023.
Adversarial Intrinsic Motivation for Reinforcement Learning 2021
Ishan Durugkar, Mauricio Tec, Scott Niekum, and Peter Stone, In Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 2021.
Importance Sampling in Reinforcement Learning with an Estimated Behavior Policy 2021
Josiah P. Hanna, Scott Niekum, and Peter Stone, Machine Learning (MLJ), Vol. 110, 6 (2021), pp. 1267–1317.
Zero-shot Task Adaptation using Natural Language 2021
Prasoon Goyal, Raymond J. Mooney, Scott Niekum, Arxiv (2021).
PixL2R: Guiding Reinforcement Learning using Natural Language by Mapping Pixels to Rewards 2020
Prasoon Goyal, Scott Niekum, Raymond J. Mooney, In 4th Conference on Robot Learning (CoRL), November 2020. Also presented on the 1st Language in Reinforcement Learning (LaReL) Workshop at ICML, July 2020 (Best Paper Award), the 6th Deep Rein...
The EMPATHIC Framework for Task Learning from Implicit Human Feedback 2020
Yuchen Cui, Qiping Zhang, Alessandro Allievi, Peter Stone, Scott Niekum, and W. Bradley Knox, In Proceedings of the 4th Conference on Robot Learning (CoRL 2020), Cambridge MA, USA, November 2020.
Importance Sampling Policy Evaluation with an Estimated Behavior Policy 2019
Josiah Hanna, Scott Niekum, and Peter Stone, In Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, California, U.S.A., June 2019.
Using Natural Language for Reward Shaping in Reinforcement Learning 2019
Prasoon Goyal, Scott Niekum, Raymond J. Mooney, In Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, August 2019.
Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation 2017
Josiah Hanna, Peter Stone, and Scott Niekum, In Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Sao Paolo, Brazil, May 2017.
Data-Efficient Policy Evaluation Through Behavior Policy Search 2017
Josiah Hanna, Philip Thomas, Peter Stone, and Scott Niekum, In Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, August 2017.
Labs
Currently affiliated with The Personal Autonomous Robotics Lab (PeARL)