8 papers
Is Your Conditional Diffusion Model Actually Denoising?
Daniel Pfrommer, Zehao Dou, Christopher Scarvelis +2
We study the inductive biases of diffusion models with a conditioning-variable, which have seen widespread application as both text-conditioned generative image models and observat…
Much Ado About Noising: Dispelling the Myths of Generative Robotic Control
Chaoyi Pan, Giri Anantharaman, Nai-Chieh Huang +8
Generative models, like flows and diffusions, have recently emerged as popular and efficacious policy parameterizations in robotics. There has been much speculation as to the facto…
Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
Thomas T. Zhang, Daniel Pfrommer, Chaoyi Pan +2
This paper presents a theoretical analysis of two of the most impactful interventions in modern learning from demonstration in robotics and continuous control: the practice of acti…
A Test-Function Approach to Incremental Stability
Daniel Pfrommer, Max Simchowitz, Ali Jadbabaie
This paper presents a novel framework for analyzing Incremental-Input-to-State Stability (ISS) based on the idea of using rewards as "test functions." Whereas control theory tra…
The Pitfalls of Imitation Learning when Actions are Continuous
Max Simchowitz, Daniel Pfrommer, Ali Jadbabaie
We study the problem of imitating an expert demonstrator in a discrete-time, continuous state-and-action control system. We show that, even if the dynamics satisfy a control-theore…
Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior
Adam Block, Ali Jadbabaie, Daniel Pfrommer +2
We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. Our framework invokes low-level controllers - either le…
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…
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…