146 citations · 565 across the 24 of their papers we have counts for
10 papers · 1 filter
Error whitening: Why Gauss-Newton outperforms Newton
Maricela Best McKay, Nathan P. Lawrence, Brian Wetton +1
The Gauss-Newton matrix is widely viewed as a positive semidefinite approximation of the Hessian, yet mounting empirical evidence shows that Gauss-Newton descent outperforms Newton…
Soft MPCritic: Value-Based Reinforcement Learning for Non-Differentiable Predictive Control
Thomas Banker, Nathan P. Lawrence, Ali Mesbah
Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet existing MPC-RL frameworks commonly rely on gradient-based optimization and theref…
Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control
Nathan P. Lawrence, Ali Mesbah
Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis o…
ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks
Pritam Dash, Ethan Chan, Nathan P. Lawrence +1
Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physical attacks, such as GPS spoofing,…
MPCritic: A plug-and-play MPC architecture for reinforcement learning
Nathan P. Lawrence, Thomas Banker, Ali Mesbah
The reinforcement learning (RL) and model predictive control (MPC) communities have developed vast ecosystems of theoretical approaches and computational tools for solving optimal…
Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior
Nathan P. Lawrence, Philip D. Loewen, Shuyuan Wang +2
We propose a framework for the design of feedback controllers that combines the optimization-driven and model-free advantages of deep reinforcement learning with the stability guar…
Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey
R. Bhushan Gopaluni, Aditya Tulsyan, Benoit Chachuat +6
Over the last ten years, we have seen a significant increase in industrial data, tremendous improvement in computational power, and major theoretical advances in machine learning.…
Meta-Reinforcement Learning for Adaptive Control of Second Order Systems
Daniel G. McClement, Nathan P. Lawrence, Michael G. Forbes +3
Meta-learning is a branch of machine learning which aims to synthesize data from a distribution of related tasks to efficiently solve new ones. In process control, many systems hav…
Almost Surely Stable Deep Dynamics
Nathan P. Lawrence, Philip D. Loewen, Michael G. Forbes +2
We introduce a method for learning provably stable deep neural network based dynamic models from observed data. Specifically, we consider discrete-time stochastic dynamic models, a…
A Meta-Reinforcement Learning Approach to Process Control
Daniel G. McClement, Nathan P. Lawrence, Philip D. Loewen +3
Meta-learning is a branch of machine learning which aims to quickly adapt models, such as neural networks, to perform new tasks by learning an underlying structure across related t…