18 citations · 35 across the 13 of their papers we have counts for
15 papers
Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations
Cevahir Koprulu, Po-han Li, Tianyu Qiu +5
Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to…
Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models
Jacob Levy, Tyler Westenbroek, David Fridovich-Keil
Traditionally, model-based reinforcement learning (MBRL) methods exploit neural networks as flexible function approximators to represent unknown environment dyn…
Enabling Efficient, Reliable Real-World Reinforcement Learning with Approximate Physics-Based Models
Tyler Westenbroek, Jacob Levy, David Fridovich-Keil
We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a pro…
The Power of Learned Locally Linear Models for Nonlinear Policy Optimization
Daniel Pfrommer, Max Simchowitz, Tyler Westenbroek +2
A common pipeline in learning-based control is to iteratively estimate a model of system dynamics, and apply a trajectory optimization algorithm - e.g.~ - on the lea…
Lyapunov Design for Robust and Efficient Robotic Reinforcement Learning
Tyler Westenbroek, Fernando Castaneda, Ayush Agrawal +2
Recent advances in the reinforcement learning (RL) literature have enabled roboticists to automatically train complex policies in simulated environments. However, due to the poor s…
On the Computational Consequences of Cost Function Design in Nonlinear Optimal Control
Tyler Westenbroek, Anand Siththaranjan, Mohsin Sarwari +2
Optimal control is an essential tool for stabilizing complex nonlinear systems. However, despite the extensive impacts of methods such as receding horizon control, dynamic programm…
On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective
Tyler Westenbroek, Max Simchowitz, Michael I. Jordan +1
%!TEX root = LCSS_main_max.tex The widespread adoption of nonlinear Receding Horizon Control (RHC) strategies by industry has led to more than 30 years of intense research efforts…
Improving Input-Output Linearizing Controllers for Bipedal Robots via Reinforcement Learning
Fernando Castañeda, Mathias Wulfman, Ayush Agrawal +4
The main drawbacks of input-output linearizing controllers are the need for precise dynamics models and not being able to account for input constraints. Model uncertainty is common…
Learning Min-norm Stabilizing Control Laws for Systems with Unknown Dynamics
Tyler Westenbroek, Fernando Castaneda, Ayush Agrawal +2
This paper introduces a framework for learning a minimum-norm stabilizing controller for a system with unknown dynamics using model-free policy optimization methods. The approach b…
Feedback Linearization for Unknown Systems via Reinforcement Learning
Tyler Westenbroek, David Fridovich-Keil, Eric Mazumdar +4
We present a novel approach to control design for nonlinear systems which leverages model-free policy optimization techniques to learn a linearizing controller for a physical plant…
Competitive Statistical Estimation with Strategic Data Sources
Tyler Westenbroek, Roy Dong, Lillian J. Ratliff +1
In recent years, data has played an increasingly important role in the economy as a good in its own right. In many settings, data aggregators cannot directly verify the quality of…
A New Solution Concept and Family of Relaxations for Hybrid Dynamical Systems
Tyler Westenbroek, Humberto Gonzalez, S. Shankar Sastry
We introduce a holistic framework for the analysis, approximation and control of the trajectories of hybrid dynamical systems which display event-triggered discrete jumps in the co…
On the Relaxation of Hybrid Dynamical Systems
Tyler Westenbroek, S. Shankar Sastry, Humberto Gonzalez
Hybrid dynamical systems have proven to be a powerful modeling abstraction, yet fundamental questions regarding the dynamical properties of these systems remain. In this paper, we…
Statistical Estimation with Strategic Data Sources in Competitive Settings
Tyler Westenbroek, Roy Dong, Lillian J. Ratliff +1
In this paper, we introduce a preliminary model for interactions in the data market. Recent research has shown ways in which a data aggregator can design mechanisms for users to en…
Optimal Control of Hybrid Systems Using a Feedback Relaxed Control Formulation
Tyler Westenbroek, Humberto Gonzalez
We present a numerically tractable formulation for computing the optimal control of the class of hybrid dynamical systems whose trajectories are continuous. Our formulation, an ext…