I am an Associate Professor and the director of the Safe, Confident, and Aligned Learning + Robotics Lab (SCALAR) in the College of Information and Computer Sciences at The University of Massachusetts Amherst. I am also a core member of the interdepartmental UMass robotics group, as well as an Adjunct Professor at the University of Texas at Austin.
The goal of my research is to ensure that AI systems are well-aligned with human objectives and can be deployed safely in the real world. Toward this goal, we develop efficient learning algorithms that enforce safety constraints, provide performance guarantees, and infer and align human and agent objectives. We work in a wide range of problem settings, from large language models to robotics, drawing from imitation learning, reinforcement learning, AI safety, and human factors.
I am a recipient of the NSF CAREER Award, the AFOSR Young Investigator Award, and the UT Austin CNS Teaching Excellence Award.
Representative Publications
Alignment, RLHF, and reward inference
-
D.S. Brown, R. Coleman, R. Srinivasan, and S. Niekum.
Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences.
International Conference on Machine Learning (ICML), July 2020.
[Project Page and Code] -
D.S. Brown, W. Goo, and S. Niekum.
Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations.
Conference on Robot Learning (CoRL), October 2019.
[Project Page and Code] -
W. Knox, S. Hatgis-Kessell, S. Booth, S. Niekum, P. Stone, A. Allievi.
Models of Human Preference for Learning Reward Functions.
Transactions on Machine Learning Research (TMLR), January 2024. -
D.S. Brown, J. Schneider, A. Dragan, and S. Niekum.
Value Alignment Verification.
International Conference on Machine Learning (ICML), July 2021.
[Project Page and Code]
-
H. Sikchi, A. Zhang, S. Niekum.
Dual RL: Unification and New Methods for Reinforcement and Imitation Learning.
International Conference on Learning Representations (ICLR), May 2024.
[Code] -
M. Alshiekh, R. Bloem, R. Ehlers, B. Könighofer, S. Niekum, and U. Topcu.
Safe Reinforcement Learning via Shielding.
AAAI Conference on Artificial Intelligence, February 2018. -
J.P. Hanna, P.S. Thomas, P. Stone, and S. Niekum.
Data-Efficient Policy Evaluation Through Behavior Policy Search.
International Conference on Machine Learning (ICML), August 2017.
-
A. Jain, R. Lioutikov, C. Chuck, and S. Niekum.
ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory.
IEEE International Conference on Robotics and Automation (ICRA), June 2021.
[Code] -
A. Jain and S. Niekum.
Efficient Hierarchical Robot Motion Planning Under Uncertainty and Hybrid Dynamics.
Conference on Robot Learning (CoRL), October 2018.
[Code] [Video]
-
Y. Cui, Q. Zhang, A. Allievi, P. Stone, S. Niekum, and W. Knox.
The EMPATHIC Framework for Task Learning from Implicit Human Feedback.
Conference on Robot Learning (CoRL), November 2020.
[Project Page and Code] -
A. Saran, R. Zhang, E.S. Short, and S. Niekum.
Efficiently Guiding Imitation Learning Algorithms with Human Gaze.
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2021.
[Code]