146 citations · 565 across the 24 of their papers we have counts for
24 papers
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…
The Separation Principle and the Dual-Certainty Equivalence Gap in Model Predictive Control
Tren Baltussen, Nathan P. Lawrence, Alexander Katriniok +2
Dual control addresses the trade-off between exploitation and exploration, where control inputs both regulate the system and generate informative data for estimation and identifica…
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…
Local-Global Learning of Interpretable Control Policies: The Interface between MPC and Reinforcement Learning
Thomas Banker, Nathan P. Lawrence, Ali Mesbah
Making optimal decisions under uncertainty is a shared problem among distinct fields. While optimal control is commonly studied in the framework of dynamic programming, it is appro…
A view on learning robust goal-conditioned value functions: Interplay between RL and MPC
Nathan P. Lawrence, Philip D. Loewen, Michael G. Forbes +2
Reinforcement learning (RL) and model predictive control (MPC) offer a wealth of distinct approaches for automatic decision-making under uncertainty. Given the impact both fields h…
Guiding Reinforcement Learning with Incomplete System Dynamics
Shuyuan Wang, Jingliang Duan, Nathan P. Lawrence +4
Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on…
Deep Hankel matrices with random elements
Nathan P. Lawrence, Philip D. Loewen, Shuyuan Wang +2
Willems' fundamental lemma enables a trajectory-based characterization of linear systems through data-based Hankel matrices. However, in the presence of measurement noise, we ask:…
Machine learning for industrial sensing and control: A survey and practical perspective
Nathan P. Lawrence, Seshu Kumar Damarla, Jong Woo Kim +7
With the rise of deep learning, there has been renewed interest within the process industries to utilize data on large-scale nonlinear sensing and control problems. We identify key…
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…
Reinforcement Learning with Partial Parametric Model Knowledge
Shuyuan Wang, Philip D. Loewen, Nathan P. Lawrence +2
We adapt reinforcement learning (RL) methods for continuous control to bridge the gap between complete ignorance and perfect knowledge of the environment. Our method, Partial Knowl…
A modular framework for stabilizing deep reinforcement learning control
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…
Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system
Tobi Michael Alabi, Nathan P. Lawrence, Lin Lu +2
The carbon-capturing process with the aid of CO2 removal technology (CDRT) has been recognised as an alternative and a prominent approach to deep decarbonisation. However, the main…
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…
Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approach
Daniel G. McClement, Nathan P. Lawrence, Johan U. Backstrom +3
Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, ma…
Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning
Nathan P. Lawrence, Michael G. Forbes, Philip D. Loewen +3
Deep reinforcement learning (RL) is an optimization-driven framework for producing control strategies for general dynamical systems without explicit reliance on process models. Goo…
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…
Optimal PID and Antiwindup Control Design as a Reinforcement Learning Problem
Nathan P. Lawrence, Gregory E. Stewart, Philip D. Loewen +3
Deep reinforcement learning (DRL) has seen several successful applications to process control. Common methods rely on a deep neural network structure to model the controller or pro…
Reinforcement Learning based Design of Linear Fixed Structure Controllers
Nathan P. Lawrence, Gregory E. Stewart, Philip D. Loewen +3
Reinforcement learning has been successfully applied to the problem of tuning PID controllers in several applications. The existing methods often utilize function approximation, su…
Deep Reinforcement Learning for Process Control: A Primer for Beginners
Steven Spielberg, Aditya Tulsyan, Nathan P. Lawrence +2
Advanced model-based controllers are well established in process industries. However, such controllers require regular maintenance to maintain acceptable performance. It is a commo…