Control of a polyol process using reinforcement learning
Reinforcement learning is a branch of machine learning, where an agent gradually learns a
control policy via a combination of exploration and interactions with a system. Recent …
control policy via a combination of exploration and interactions with a system. Recent …
Learning to Tune a Class of Controllers with Deep Reinforcement Learning
WJ Shipman - Minerals, 2021 - mdpi.com
Control systems require maintenance in the form of tuning their parameters in order to
maximize their performance in the face of process changes in minerals processing circuits …
maximize their performance in the face of process changes in minerals processing circuits …
Cooktop appliance with a gas burner
DW Billman, JA Yantis - US Patent 11,015,813, 2021 - Google Patents
A cooktop appliance includes a user interface, a gas burner, and a temperature sensor. A
manually adjustable primary control valve is coupled to the gas burner. A secondary control …
manually adjustable primary control valve is coupled to the gas burner. A secondary control …
Tuning pid parameters using causal models
BE Brooks, GJ Benoit, PO Olson, TW Olson… - US Patent App. 17 …, 2022 - Google Patents
(52) US CI. CPC G05B 6/02 (2013.01)(57) ABSTRACT Methods, systems, and apparatus,
including computer pro grams encoded on a computer storage medium, for optimiz ing …
including computer pro grams encoded on a computer storage medium, for optimiz ing …
Initialization of radial base function neural network nodes for reinforcement learning incremental control system
S Hurley, B Wilson, D McCleary - US Patent 11,879,656, 2024 - Google Patents
According to one or more embodiments of the present invention, a computer-implemented
method for adjusting a process variable using a closed loop system includes initializing a …
method for adjusting a process variable using a closed loop system includes initializing a …
Method and system for directly tuning PID parameters using a simplified actor-critic approach to reinforcement learning
(57) ABSTRACT A method and system for reinforcement learning can include an actor-critic
framework comprising an actor and a critic, the actor comprising an actor network and the …
framework comprising an actor and a critic, the actor comprising an actor network and the …
Application of simple random search approach for reinforcement learning to controller tuning parameters
A method and system for reinforcement learning can involve applying a finite-difference
approach to a controller, and tuning the controller in response to applying the finite …
approach to a controller, and tuning the controller in response to applying the finite …
Apparatus, method and storage medium
G Takami - US Patent App. 17/088,607, 2021 - Google Patents
An apparatus is provided, which includes a first acquisition unit for acquiring measurement
data measured by a sensor and a first learning processing unit for executing, by using …
data measured by a sensor and a first learning processing unit for executing, by using …
Electric power converter
S Nazir, BL Schwabe - US Patent 11,132,009, 2021 - Google Patents
An electric switch-mode power converter comprises: a parameter predictor for predicting and
updating at least one regulator parameter of a regulator controlling a switching device of the …
updating at least one regulator parameter of a regulator controlling a switching device of the …
Methods and systems to adapt pid coefficients through reinforcement learning
Systems and methods are used to adapt the coefficients of a proportional-integral-derivative
(PID) controller through reinforcement learning. The approach for adapting PID coefficients …
(PID) controller through reinforcement learning. The approach for adapting PID coefficients …