Santiago Paternain
 |
Santiago Paternain Assistant Professor Office: 6034 Jonsson Engineering Center |
About me
I am an Assistant Professor at the Electrical, Computer and Systems Engineering Department at Rensselaer Polytechnic Institute. Prior to that I was a Postdoctoral Researcher at the Univerisity of Pennsylvania where I also received my Ph.D. in Electrical in Systems Engineering under the supervision of Alejandro Ribeiro.
My research interests lie at the intersection of machine learning and control of dynamical systems.
News
October 2025: Our paper “Random Policy Enables In-Context Reinforcement Learning within Trust Horizons” published in TMLR received the J2C certification
October 2025: Congratulations to Weiqin Chen for being awarded on of the highest honors at RPI: the 2025 Founders Award of Excellence.
September 2025: Our paper on “Dynamic Decomposition DISC” has been accepted to NeuRIPS.
July 2025: Three papers accepted in the Conference on Decision and Control (CDC).
June 2025: Our paper A “Bi-Level Optimization Method for Redundant Dual-Arm Minimum Time Problems” was published in the IEEE Control Systems Letters
May 2025: Awarded an exploratory grant by the RPI-IBM Future of Computing Research Collaboration QUANTUM
April 2025: Our paper “Random Policy Enables In-Context Reinforcement Learning within Trust Horizons” was published in TMLR
January 2025: Two papers accepted in the American Control Conference (ACC).
December 2024: Awarded an exploratory grant by the RPI-IBM Future of Computing Research Collaboration to investigate techniques to improve the reasoning capabilties of LLMs.
November 2024: Awarded an DOE grant for “On-site testing and disassembly to enable hierarchical residual value assessments of EV LIB packs at a collection site”
September 2024: One paper accepted to the “IEEE Transactions on Power Systems” and a paper accepted to the IEEE Robotics and Automation Letters.
August 2024: We deliverd a organizing a tutorial on “Learning under Requirements” at EUSIPCO.
July 2024: Congratulations to Glory Justin for the Defense of her Ph.D. “Graph Neural Networks for Power Grid Stability” and the acceptance of a journal paper.
July 2024: We are organizing a tutorial on “Learning under Requirements” at L4DC.
April 2024: Two papers accepted at the Conference for Learning and Control (L4DC).
March 2024: Our paper “Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning” has been accepted for publication in the IEEE Transactions on Signal Processing.
March 2024: Our paper “Probabilistic Constraint for Safety-Critical Reinforcement Learning” has been accepted for publication in the IEEE Transactions on Automatic Control.
February 2024: We organized a tutorial on “Learning under Requirements” at AAAI with more than 180 registered attendants.
February 2024: Congratulations to Weiqin Chen for being awarded the 2023 Belsky Award for Computational Sciences and Engineering by the School of Engineering.
January 2024: Two papers accepted in the American Control Conference (ACC).
January 2024: Our paper has been accepted in the International Conference on Autonomous Agents and Multi-Agent Systems.
November 2023: Awarded an exploratory grant by the RPI-IBM AI Research Center to control based techniques reinforcement learning.
September 2023: Our paper “State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards” has been accepted for publication in the IEEE Transactions on Automatic Control.
January 2023: Awarded an ONR grant for ‘‘A framework for Combining Model-based and Data-driven Control for Autonomous Helicopter Aerial Refueling’’.
November 2022: Awarded an exploratory grant by the RPI-IBM AI Research Center to investigate techniques to improve hyperparameter optimization for safe reinforcement learning.
August 2022: Our paper “Navigation of a Quadratic Potential with Ellipsoidal Obstacles” has been accepted for publication in Automatica.
June 2022: Our paper “Constrained Learning with Non-Convex Losses” has been accepted for publication in the IEEE Transactions on Information Theory.
June 2022: Awarded a grant with The Boeing Company for Systems Installation Robotic Assist.
March 2022: Our paper “Policy Gradient for Continuing Tasks in Discounted Markov Decision Processes” has been accepted for publication in the IEEE Transactions on Automatic Control.
February 2022: Our paper “Safe Policies for Reinforcement Learning via Primal-Dual Methods” has been accepted for publication in the IEEE Transactions on Automatic Control.
October 2021: Our paper “State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards” has been accepted to be presented in the Nurips workshop on Safe and Robust Control of Uncertain Systems.
October 2021: Awarded an exploratory grant by the RPI-IBM AI Research Center to investigate improvements to model learning for model-based reinforcement learning.
September 2021: Awared a grant by the Advanced Robotics for Manufacturing (ARM) ‘‘Robot Motion Program for Tracking Complex Geometric Paths’’ (CO-PI).
February 2021: Two papers accepted in the American Control Conference (ACC).
August 2020: I started a position as Assistant Professor at the Electrical, Computer and Systems Engineering Department at Rensselaer Polytechnic Institute.