Optimal Control Method Based on Supervised Reinforcement Learning
A technology of reinforcement learning and optimal control, applied in adaptive control, general control system, control/regulation system, etc., can solve the problems of low learning success rate and high training cost
Active Publication Date: 2016-03-02
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] Aiming at the problems of high training cost and low learning success rate of the traditional reinforcement learning control method, the present invention proposes an optimal control method based on supervised reinforcement learning
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0019] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings.
[0020] In the method of the present invention, the supervisory controller is an existing non-optimal controller, such as a PID controller. In the initial training process, the supervisory controller endows the controller with some prior knowledge, effectively reducing the reinforcement The training difficulty of learning. At the same time, the tutor-supervised learning cannot provide all the optimal information, and the exploration process of reinforcement learning needs to be introduced to achieve optimization, and the exploration process can be effectively evaluated and fed back to the controller through the evaluator. Ultimately, the optimal control method based on supervised reinforcement learning can make the controller and evaluator neural network iteratively conver...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an optimal control method based on supervised reinforcement learning. The method comprises the steps: 1, initializing parameters such as a weight value of an artificial neural network of a controller and an evaluator, and a training data set, 2, selecting a set of system states to be iterated, 3, generating an initial stable control strategy through the supervised controller and approaching the control strategy through regulating a weight value of the controller, 4, generating a corresponding control action through the controller and adding a certain amount of random noise as exploration, 5, exerting the control action with the noise on a controlled system and observing the state and return of the system in the next moment, 6, regulating the weight of the artificial neural network of the controller and the evaluator, 7, judging whether the current state meets an end condition or not, if yes, entering the step 8, and if not, returning to the step 3, and 8, judging whether initial system state data are all used for training or not, if yes, outputting the data from the final controller, and if not, returning to the step 2.
Description
technical field [0001] The invention relates to the technical field of intelligent control, in particular to an optimal control method based on supervised reinforcement learning. Background technique [0002] In the fields of industrial production, aerospace, automotive engineering, etc., the controlled system can use the smallest resources to complete the control goal under limited resources, that is, optimal control. Optimal control refers to finding an optimal control strategy that can make the performance index function optimal. The performance index function is related to the system state and the adopted control strategy, and it can reflect the control effect of the control strategy at present and in the future. The performance index function for discrete systems can be expressed in mathematical form as follows: [0003] J ( x k ) = Σ ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/02
Inventor 赵冬斌王滨刘德荣
Owner INST OF AUTOMATION CHINESE ACAD OF SCI