Search Results for author: Tyler Westenbroek

Found 9 papers, 2 papers with code

Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models

1 code implementation11 Oct 2024 Jacob Levy, Tyler Westenbroek, David Fridovich-Keil

We leverage this capability and propose Semi-Structured Reinforcement Learning ($\texttt{SSRL}$) a simple model-based learning framework which pushes the sample complexity boundary for real-world learning.

Model-based Reinforcement Learning reinforcement-learning +1

Enabling Efficient, Reliable Real-World Reinforcement Learning with Approximate Physics-Based Models

1 code implementation16 Jul 2023 Tyler Westenbroek, Jacob Levy, David Fridovich-Keil

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data.

Policy Gradient Methods

The Power of Learned Locally Linear Models for Nonlinear Policy Optimization

no code implementations16 May 2023 Daniel Pfrommer, Max Simchowitz, Tyler Westenbroek, Nikolai Matni, Stephen Tu

A common pipeline in learning-based control is to iteratively estimate a model of system dynamics, and apply a trajectory optimization algorithm - e. g.~$\mathtt{iLQR}$ - on the learned model to minimize a target cost.

On the Computational Consequences of Cost Function Design in Nonlinear Optimal Control

no code implementations5 Apr 2022 Tyler Westenbroek, Anand Siththaranjan, Mohsin Sarwari, Claire J. Tomlin, Shankar S. Sastry

However, despite the extensive impacts of methods such as receding horizon control, dynamic programming and reinforcement learning, the design of cost functions for a particular system often remains a heuristic-driven process of trial and error.

reinforcement-learning Reinforcement Learning +1

On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective

no code implementations27 Mar 2021 Tyler Westenbroek, Max Simchowitz, Michael I. Jordan, S. Shankar Sastry

Crucially, this guarantee requires that state costs applied to the planning problems are in a certain sense `compatible' with the global geometry of the system, and a simple counter-example demonstrates the necessity of this condition.

Technical Report: Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning

no code implementations6 Apr 2020 Tyler Westenbroek, Eric Mazumdar, David Fridovich-Keil, Valmik Prabhu, Claire J. Tomlin, S. Shankar Sastry

This paper proposes a framework for adaptively learning a feedback linearization-based tracking controller for an unknown system using discrete-time model-free policy-gradient parameter update rules.

reinforcement-learning Reinforcement Learning +1

Feedback Linearization for Unknown Systems via Reinforcement Learning

no code implementations29 Oct 2019 Tyler Westenbroek, David Fridovich-Keil, Eric Mazumdar, Shreyas Arora, Valmik Prabhu, S. Shankar Sastry, Claire J. Tomlin

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 with unknown dynamics.

reinforcement-learning Reinforcement Learning +1

Competitive Statistical Estimation with Strategic Data Sources

no code implementations29 Apr 2019 Tyler Westenbroek, Roy Dong, Lillian J. Ratliff, S. Shankar Sastry

Recent work has explored mechanisms to ensure that the data sources share high quality data with a single data aggregator, addressing the issue of moral hazard.

Cannot find the paper you are looking for? You can Submit a new open access paper.