Robert D. McAllister
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Robert D. McAllister has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- James B. Rawlings
Department of Chemical Engineering University of California Santa Barbara
6 shared publications - Bart van Laatum3 shared publications
- Eldert J. van Henten
Farm Technology, Department of Plant Sciences, Wageningen University and Research, 6700 AA Wageningen, The Netherlands
3 shared publications - Salim Msaad3 shared publications
- Sjoerd Boersma3 shared publications
James B. Rawlings
Department of Chemical Engineering, University of California, Santa Barbara, Santa Barbara, California93106, United States
2 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 254
Improving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control
- 7 October 2026
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 254
Open AccessImproving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control
- Open Access
- 15 June 2026
- Published by Elsevier in SSRN Electronic Journal
Improving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control
Greenhouse fruit-production control aims to maximize the economic performance (fruit revenue minus operating costs) while operating within system constraints under external weather disturbances. Control methods need to balance the delayed economic benefit of fruit yield with current operating costs. For such problems, model predictive control (MPC) can explicitly handle system constraints under future weather disturbances, but can become computationally demanding when using sufficiently long prediction horizons for (relatively large) nonlinear greenhouse fruit production models. In contrast, reinforcement learning (RL) can learn control policies offline while considering longer-term economic performance, but struggles to enforce system constraints, and performance may degrade under unseen weather trajectories. This work proposes trajectory-selection RL--MPC, a framework that incorporates longer-term economic information of fruit yield into a short-horizon MPC optimization problem. The framework uses an RL rollout trajectory to define a terminal region constraint and terminal cost. Next, a nonlinear MPC solves a short-horizon optimization problem with these terminal ingredients to find a local optimum. Finally, the framework selects and executes the first input from the trajectory with the better objective value, either from the MPC-predicted or the RL rollout trajectory. The method is applied to GreenLight, a large-scale greenhouse tomato production model that exhibits stiff dynamics. The simulation results show that trajectory-selection RL--MPC with a one-hour prediction horizon matches the closed-loop performance of a high-performing guiding policy while significantly improving over standalone MPC with the same horizon. On 25 weather trajectories held out during policy training, trajectory-selection RL--MPC achieved 54% higher closed-loop performance than standalone RL and 80% higher performance than MPC with the same horizon length.
- 15 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessImproving greenhouse fruit-production control by integrating reinforcement learning into short-horizon model predictive control
Greenhouse fruit-production control aims to maximize the economic performance (fruit revenue minus operating costs) while operating within system constraints under external weather disturbances. Control methods need to balance the delayed economic benefit of fruit yield with current operating costs. For such problems, model predictive control (MPC) can explicitly handle system constraints under future weather disturbances, but can become computationally demanding when using sufficiently long prediction horizons for (relatively large) nonlinear greenhouse fruit production models. In contrast, reinforcement learning (RL) can learn control policies offline while considering longer-term economic performance, but struggles to enforce system constraints, and performance may degrade under unseen weather trajectories. This work proposes trajectory-selection RL--MPC, a framework that incorporates longer-term economic information of fruit yield into a short-horizon MPC optimization problem. The framework uses an RL rollout trajectory to define a terminal region constraint and terminal cost. Next, a nonlinear MPC solves a short-horizon optimization problem with these terminal ingredients to find a local optimum. Finally, the framework selects and executes the first input from the trajectory with the better objective value, either from the MPC-predicted or the RL rollout trajectory. The method is applied to GreenLight, a large-scale greenhouse tomato production model that exhibits stiff dynamics. The simulation results show that trajectory-selection RL--MPC with a one-hour prediction horizon matches the closed-loop performance of a high-performing guiding policy while significantly improving over standalone MPC with the same horizon. On 25 weather trajectories held out during policy training, trajectory-selection RL--MPC achieved 54% higher closed-loop performance than standalone RL and 80% higher performance than MPC with the same horizon length.
- Open Access
- 21 January 2026
- Published by Elsevier in Control Engineering Practice
- Vol. 169
Stochastic model predictive control with reinforcement learning for greenhouse production systems under parametric uncertainty
- 21 January 2026
- Published by Elsevier in Control Engineering Practice
- Vol. 169
Open AccessStochastic model predictive control with reinforcement learning for greenhouse production systems under parametric uncertainty
- Top Cited Papers
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (1) , 395-410
AC4MPC: Actor-Critic Reinforcement Learning for Guiding Model Predictive Control
Nonlinear model predictive control (MPC) and reinforcement learning (RL) are two powerful control strategies with complementary advantages. This work shows how actor-critic RL techniques can be leveraged to improve the performance of MPC. The RL critic is used as an approximation of the optimal value function, and an actor rollout provides an initial guess for the primal variables of the MPC. A parallel control architecture is proposed where each MPC instance is solved twice for different initial guesses. Besides the actor rollout initialization, a shifted initialization from the previous solution is used. The control actions from the lowest-cost trajectory are applied to the system at each time step. We provide some theoretical justification of the proposed algorithm by establishing that the discounted closed-loop cost is upper-bounded by the discounted closed-loop cost of the original RL actor plus an error term that depends on the (sub)optimality of the RL actor and the accuracy of the critic. These results do not require globally optimal solutions and indicate that larger horizons mitigate the effect of errors in the critic approximation. The proposed algorithm is intended for applications where standard methods to construct terminal costs or constraints for MPC are impractical. The approach is demonstrated in an illustrative toy example and an autonomous driving overtaking scenario.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (1) , 395-410
Top Cited PapersAC4MPC: Actor-Critic Reinforcement Learning for Guiding Model Predictive Control
Nonlinear model predictive control (MPC) and reinforcement learning (RL) are two powerful control strategies with complementary advantages. This work shows how actor-critic RL techniques can be leveraged to improve the performance of MPC. The RL critic is used as an approximation of the optimal value function, and an actor rollout provides an initial guess for the primal variables of the MPC. A parallel control architecture is proposed where each MPC instance is solved twice for different initial guesses. Besides the actor rollout initialization, a shifted initialization from the previous solution is used. The control actions from the lowest-cost trajectory are applied to the system at each time step. We provide some theoretical justification of the proposed algorithm by establishing that the discounted closed-loop cost is upper-bounded by the discounted closed-loop cost of the original RL actor plus an error term that depends on the (sub)optimality of the RL actor and the accuracy of the critic. These results do not require globally optimal solutions and indicate that larger horizons mitigate the effect of errors in the critic approximation. The proposed algorithm is intended for applications where standard methods to construct terminal costs or constraints for MPC are impractical. The approach is demonstrated in an illustrative toy example and an autonomous driving overtaking scenario.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (5) , 2963-2978
Distributionally Robust Model Predictive Control: Closed-Loop Guarantees and Scalable Algorithms
We establish a collection of closed-loop guarantees and propose a scalable optimization algorithm for distributionally robust model predictive control (DRMPC) applied to linear systems, convex constraints, and quadratic costs. Via standard assumptions for the terminal cost and constraint, we establish distributionally robust long-term and stagewise performance guarantees for the closed-loop system. We further demonstrate that a common choice of the terminal cost, i.e., via the discrete-algebraic Riccati equation, renders the origin input-to-state stable for the closed-loop system. This choice also ensures that the exact long-term performance of the closed-loop system is independent of the choice of ambiguity set for the DRMPC formulation. Thus, we establish conditions under which DRMPC does not provide a long-term performance benefit relative to stochastic MPC. To solve the DRMPC optimization problem, we propose a Newton-type algorithm that empirically achieves superlinear convergence and guarantees the feasibility of each iterate. We demonstrate the implications of the closed-loop guarantees and the scalability of the proposed algorithm via two examples. To facilitate the reproducibility of the results, we also provide open-source code to implement the proposed algorithm and generate the figures.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (5) , 2963-2978
Distributionally Robust Model Predictive Control: Closed-Loop Guarantees and Scalable Algorithms
We establish a collection of closed-loop guarantees and propose a scalable optimization algorithm for distributionally robust model predictive control (DRMPC) applied to linear systems, convex constraints, and quadratic costs. Via standard assumptions for the terminal cost and constraint, we establish distributionally robust long-term and stagewise performance guarantees for the closed-loop system. We further demonstrate that a common choice of the terminal cost, i.e., via the discrete-algebraic Riccati equation, renders the origin input-to-state stable for the closed-loop system. This choice also ensures that the exact long-term performance of the closed-loop system is independent of the choice of ambiguity set for the DRMPC formulation. Thus, we establish conditions under which DRMPC does not provide a long-term performance benefit relative to stochastic MPC. To solve the DRMPC optimization problem, we propose a Newton-type algorithm that empirically achieves superlinear convergence and guarantees the feasibility of each iterate. We demonstrate the implications of the closed-loop guarantees and the scalability of the proposed algorithm via two examples. To facilitate the reproducibility of the results, we also provide open-source code to implement the proposed algorithm and generate the figures.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 69 (2) , 1242-1248
A Suboptimal Economic Model Predictive Control Algorithm for Large and Infrequent Disturbances
We present a suboptimal economic model predictive control (MPC) algorithm that combines the strengths of two common suboptimal MPC approaches, one based on a warm-start and one based on an optimality gap. This algorithm is specifically designed to address a class of large and infrequent disturbances that are relevant when considering discrete actuators and production scheduling in control problems. We establish that this algorithm provides the same nominal performance guarantee as optimal economic MPC and is inherently robust, in an economic context, to large and infrequent disturbances. This inherent robustness guarantee is not attained by either individual algorithm. We conclude with a small production scheduling example to demonstrate the benefits of the proposed algorithm for a practical application.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 69 (2) , 1242-1248
A Suboptimal Economic Model Predictive Control Algorithm for Large and Infrequent Disturbances
We present a suboptimal economic model predictive control (MPC) algorithm that combines the strengths of two common suboptimal MPC approaches, one based on a warm-start and one based on an optimality gap. This algorithm is specifically designed to address a class of large and infrequent disturbances that are relevant when considering discrete actuators and production scheduling in control problems. We establish that this algorithm provides the same nominal performance guarantee as optimal economic MPC and is inherently robust, in an economic context, to large and infrequent disturbances. This inherent robustness guarantee is not attained by either individual algorithm. We conclude with a small production scheduling example to demonstrate the benefits of the proposed algorithm for a practical application.
- 5 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 69 (2) , 741-754
On the Inherent Distributional Robustness of Stochastic and Nominal Model Predictive Control
We define a notion of distributional robustness, via the Wasserstein metric, for closed-loop systems subject to errors in the disturbance distribution used to construct the controller. We then establish sufficient conditions for stochastic model predictive control (SMPC) to satisfy this definition of distributional robustness and establish a similar notion of distributional robustness for economic applications of SMPC. These results address incorrectly or unmodeled disturbances, demonstrate the efficacy of scenario optimization as a means to approximate and solve the SMPC problem, and unify the descriptions of robustness for stochastic and nominal model predictive control. This definition of distributional robustness for closed-loop systems is general and can be applied to other stochastic optimal control algorithms and, potentially, the developing field of distributionally robust control.
- 5 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 69 (2) , 741-754
On the Inherent Distributional Robustness of Stochastic and Nominal Model Predictive Control
We define a notion of distributional robustness, via the Wasserstein metric, for closed-loop systems subject to errors in the disturbance distribution used to construct the controller. We then establish sufficient conditions for stochastic model predictive control (SMPC) to satisfy this definition of distributional robustness and establish a similar notion of distributional robustness for economic applications of SMPC. These results address incorrectly or unmodeled disturbances, demonstrate the efficacy of scenario optimization as a means to approximate and solve the SMPC problem, and unify the descriptions of robustness for stochastic and nominal model predictive control. This definition of distributional robustness for closed-loop systems is general and can be applied to other stochastic optimal control algorithms and, potentially, the developing field of distributionally robust control.
- 6 December 2022
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 62 (5) , 2175-2190
On Using Feedback Control to Contend with Nature’s Randomness
- 6 December 2022
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 62 (5) , 2175-2190
On Using Feedback Control to Contend with Nature’s Randomness
- 5 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (10) , 5810-5822
The Stochastic Robustness of Nominal and Stochastic Model Predictive Control
In this work, we establish and compare the stochastic and deterministic robustness properties achieved by nominal model predictive control (MPC), stochastic MPC (SMPC), and a proposed constraint-tightened MPC (CMPC) formulation, which represents an idealized version of tube-based MPC. We consider three definitions of robustness for nonlinear systems and bounded disturbances: robust asymptotic stability (RAS), robust asymptotic stability in expectation (RASiE), and RASiE w.r.t. the stage cost $\ell (\cdot)$ used in these MPC formulations ( $\ell$ -RASiE). Via input-to-state stability (ISS) and stochastic ISS (SISS) Lyapunov functions, we establish that MPC, subject to sufficiently small disturbances, and CMPC ensure all three definitions of robustness without a stochastic objective function. While SMPC also ensures RASiE and $\ell$ -RASiE, SMPC does not guarantee RAS for nonlinear systems. Through a few simple examples, we illustrate the implications of these results and demonstrate that, depending on the definition of robustness considered, SMPC is not necessarily more robust than nominal MPC even if the disturbance model is exact.
- 5 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (10) , 5810-5822
The Stochastic Robustness of Nominal and Stochastic Model Predictive Control
In this work, we establish and compare the stochastic and deterministic robustness properties achieved by nominal model predictive control (MPC), stochastic MPC (SMPC), and a proposed constraint-tightened MPC (CMPC) formulation, which represents an idealized version of tube-based MPC. We consider three definitions of robustness for nonlinear systems and bounded disturbances: robust asymptotic stability (RAS), robust asymptotic stability in expectation (RASiE), and RASiE w.r.t. the stage cost $\ell (\cdot)$ used in these MPC formulations ( $\ell$ -RASiE). Via input-to-state stability (ISS) and stochastic ISS (SISS) Lyapunov functions, we establish that MPC, subject to sufficiently small disturbances, and CMPC ensure all three definitions of robustness without a stochastic objective function. While SMPC also ensures RASiE and $\ell$ -RASiE, SMPC does not guarantee RAS for nonlinear systems. Through a few simple examples, we illustrate the implications of these results and demonstrate that, depending on the definition of robustness considered, SMPC is not necessarily more robust than nominal MPC even if the disturbance model is exact.
- 7 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (3) , 1524-1536
Nonlinear Stochastic Model Predictive Control: Existence, Measurability, and Stochastic Asymptotic Stability
In this work, we establish a collection of new theoretical properties for nonlinear stochastic model predictive control (SMPC). Based on the concept of stochastic input-to-state stability (SISS), we define robust asymptotic stability in expectation (RASiE) and establish that nonlinear SMPC renders the origin of the closed-loop system RASiE. Moreover, we establish several new foundational results that have not been addressed in previous research. Specifically, we verify that, under basic regularity assumptions, a solution to the SMPC optimization problem exists and the closed-loop trajectory is Borel measurable thereby guaranteeing that all relevant stochastic properties of the closed-loop system are indeed well-defined. We present a numerical example to demonstrate the nonintuitive behavior that can arise from nonlinear SMPC.
- 7 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 68 (3) , 1524-1536
Nonlinear Stochastic Model Predictive Control: Existence, Measurability, and Stochastic Asymptotic Stability
In this work, we establish a collection of new theoretical properties for nonlinear stochastic model predictive control (SMPC). Based on the concept of stochastic input-to-state stability (SISS), we define robust asymptotic stability in expectation (RASiE) and establish that nonlinear SMPC renders the origin of the closed-loop system RASiE. Moreover, we establish several new foundational results that have not been addressed in previous research. Specifically, we verify that, under basic regularity assumptions, a solution to the SMPC optimization problem exists and the closed-loop trajectory is Borel measurable thereby guaranteeing that all relevant stochastic properties of the closed-loop system are indeed well-defined. We present a numerical example to demonstrate the nonintuitive behavior that can arise from nonlinear SMPC.