The power of learned locally linear models for nonlinear policy optimization
Dan Pfommer, Max Simchowitz, Tyler Westenbroek, Nikolai Matni, and Stephen Tu.
ICML 2023 (Under Review), 2023.
|
Reinforcement Learning with Simple Dynamics Models and Low-Level Feedback Controllers
Tyler Westenbroek, Mohsin Sarwari, Fernando Castaneda, Anand Siththaranjan, Claire Tomlin, Koushil Sreenath, Shankar Sastry.
Under Submission R-AL, 2022.
|
Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning
Tyler Westenbroek*, Fernando Castaneda, Ayush Agrawal, Shankar Sastry, Koushil Sreenath.
Conference on Robot Learning, 2022.
paper
|
On the Computational Consequences of Cost Function Design for Nonlinear Optimal Control
Tyler Westenbroek, Anand Siththaranjan, Mohsin Sarwari, Claire Tomlin, Shankar Sastry.
Conference on Decision and Control, 2022.
paper
|
On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective
Tyler Westenbroek*, Max Simchowitz*, Michael I. Jordan, Shankar Sastry.
Conference On Decision and Control, 2021.
paper
|
Combining Model-Based Design and Model-Free Policy Optimization to Learn Safe, Stabilizing Controllers
Tyler Westenbroek, Ayush Agrawal, Fernando Castaneda, Shankar Sastry, Koushil Sreenath.
Analysis and Design of Hybrid Systems, 2021.
paper
|
Smooth approximations for hybrid optimal control problems with application to robotic walking
Tyler Westenbroek, Xiaobin Xion, Shankar Sastry, Aaron D. Ames.
Analysis and Design of Hybrid Systems, 2021.
paper
|
Feedback linearization for uncertain systems via reinforcement learning
Tyler Westenbroek*, David Fridovich-Keil*, Eric Mazumdar, Shreyas Arora, Valmik Prabhu, Shankar Sastry, Claire Tomlin.
Internation Conference on Robotics and Automation, 2020.
paper
|
Learning min-norm stabilizing control laws for systems with unknown dynamics
Tyler Westenbroek, Eric Mazumdar, David Fridovich-Keil, Valmik Prabhu, Claire Tomlin, Shankar Sastry.
Conference on Decision and Control, 2020.
paper
|
Improving Input-Output Linearizing Controllers for Bipedal Robots via Reinforcement Learning
Fernando Castaneda, Mathias Wulfman, Ayush Agrawal, Tyler Westenbroek, Claire J. Tomlin, S. Shankar Sastry, Koushil Sreenath.
Learning for Dynamics and Control, 2020.
paper
|
High Confidence Sets for Trajectories of Stochastic Time-Varying Nonlinear Systems
Eric Mazumdar, Tyler Westenbroek, Michael I. Jordan, .
Conference on Decision and Conrtrol, 2020.
paper
|
Adaptive control for linearizable systems using on-policy reinforcement learning
Tyler Westenbroek, Eric Mazumdar, David Fridovich-Keil, Valmik Prabhu, Claire Tomlin, Shankar Sastry.
Conference on Decision and Control, 2020.
paper
|
Competitive Statistical Estimation with Strategic Data Sources
Tyler Westenbroek, Roy Dong, Lillian Ratliff, Shankar Sastry.
Transaction on Automatic Control, 2019.
paper
|
A New Solution Concept and Family of Relaxations for Hybrid Dynamical Systems
Tyler Westenbroek, Humberto Gonzalez, Shankar Sastry.
Conference on Decision and Control, 2019.
paper
|
Optimal control of piecewise-smooth control systems via singular perturbations
Tyler Westenbroek, Xiaobin Xiong, Aaron D. Ames, Shankar Sastry.
Conference on Decision and Control, 2019.
paper
|
Statistical Estimation with Strategic Data Sources in Competitive Settings
Tyler Westenbroek, Roy Dong, Lillian Ratliff, Shankar Sastry.
Conference on Decision and Control, 2017.
paper
|
|