ADAPTIVE CONTROL POLICY IN MICROPROCESSOR NETWORK PROCESSING

1990 ◽  
pp. 305-310
Author(s):  
T.A. Stoilov
Keyword(s):  
Adaptive Control ◽  
Control Policy ◽  
Network Processing

scholarly journals Complementary Meta-Reinforcement Learning for Fault-Adaptive Control

2020 ◽  
Vol 12 (1) ◽  
pp. 8
Author(s):  
Ibrahim Ahmed ◽  
Marcos Quiñones-Grueiro ◽  
Gautam Biswas
Keyword(s):  
Adaptive Control ◽  
Reinforcement Learning ◽  
Fault Tolerant ◽  
Control Policy ◽  
Time Constraints ◽  
Learning Approach ◽  
Fuel Tanks ◽  
Meta Learning ◽  
New Policies ◽  
Abrupt Faults

Faults are endemic to all systems. Adaptive fault-tolerant control accepts degraded performance under faults in exchange for continued operation. In systems with abrupt faults and strict time constraints, it is imperative for control to adapt fast to system changes. We present a meta-reinforcement learning approach that quickly adapts control policy. The approach builds upon model-agnostic meta learning (MAML). The controller maintains a complement of prior policies learned under system faults. This ``library" is evaluated on a system after a new fault to initialize the new policy. This contrasts with MAML where the controller samples new policies from a distribution of similar systems at each update step to achieve the new policy. Our approach improves sample efficiency of the reinforcement learning process. We evaluate this on a model of fuel tanks under abrupt faults.

scholarly journals Actor Critic Neural Network-Based Adaptive Control for MEMS Gyroscopes Suffering from Multiresource Disturbances

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Chao Jing ◽  
Gangzhu Qiao
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Control Method ◽  
Control Policy ◽  
Dynamic Surface Control ◽  
Order System ◽  
Dynamic Surface ◽  
Control Approach ◽  
Mems Gyroscopes ◽  
Critic Neural Network

In this paper, an actor critic neural network-based adaptive control scheme for micro-electro-mechanical system (MEMS) gyroscopes suffering from multiresource disturbances is proposed. Faced with multiresource interferences consisting of parametric uncertainties, strong couplings between axes, Coriolis forces, and variable external disturbances, an actor critic neural network is introduced, where the actor neural network is employed to estimate the packaged disturbances and the critic neural network is utilized to supervise the system performance. Hence, strong robustness against uncertainties and better tracking properties can be derived for MEMS gyroscopes. Aiming at handling the nonlinearities inherent in gyroscopes without analytically differentiating the virtual control signals, dynamic surface control (DSC) rather than backstepping control method is employed to divide the 2nd order system into two 1st order systems and design the actual control policy. Moreover, theoretical analyses along with simulation experiments are conducted with a view to validate the effectiveness of the proposed control approach.

On Performance Losses in Some Adaptive Control Systems: I

1965 ◽  
Vol 87 (1) ◽  
pp. 90-94 ◽  
Author(s):  
Masanao Aoki
Keyword(s):  
Adaptive Control ◽  
Control Systems ◽  
Unknown Parameter ◽  
A Priori ◽  
Control Policy ◽  
Optimal Estimation ◽  
Perfect Information ◽  
Point Of View ◽  
Unknown Parameters ◽  
Linear Differential

In controlling dynamic systems with unknown parameters and/or systems operating in unknown environment, the systems suffer due to the unknowness of pertinent parameter values, compared with situations with perfect information where all pertinent information is available to control systems optimally. The paper defines the concept of loss of performance to represent the loss in performance of some adaptive control situations compared with perfect information situations and defines the optimal control problems as the one where the loss of performance is minimized. This concept is illustrated for a control system governed by a scalar linear differential equation with unknown gain. The minimax control policy is defined as the control policy which minimized the maximum possible loss in performance where no a priori knowledge on the unknown parameter is available. It also discusses the optimal estimation problem of the unknown parameter from the point of view of loss of performance.

An actively adaptive control policy for linear models

1996 ◽  
Vol 41 (6) ◽  
pp. 855-858 ◽  
Author(s):  
L. Pronzato ◽  
C. Kulcsar ◽  
E. Walter
Keyword(s):  
Adaptive Control ◽  
Linear Models ◽  
Control Policy

GA-Based Q-CMAC Applied to Airship Evasion Problem

1998 ◽  
Vol 10 (5) ◽  
pp. 431-438 ◽  
Author(s):  
Yuka Akisato ◽  
◽  
Keiji Suzuki ◽  
Azuma Ohuchi
Keyword(s):  
Adaptive Control ◽  
Reinforcement Learning ◽  
State Space ◽  
Control Policy ◽  
The State ◽  
Space Layer ◽  
Construction Simulation ◽  
Q Learning ◽  
Evolutionary State ◽  
Evasion Problem

The purpose of this research is to acquire an adaptive control policy of an airship in a dynamic, continuous environment based on reinforcement learning combined with evolutionary construction. The state space for reinforcement learning becomes huge because the airship has great inertia and must sense huge amounts of information from a continuous environment to behave appropriately. To reduce and suitably segment state space, we propose combining CMAC-based Q-learning and its evolutionary state space layer construction. Simulation showed the acquisition of state space segmentation enabling airships to learn effectively.

An Adaptive Control Policy of Discrete-Time Linear Systems With Random Parameters

1979 ◽  
Vol 101 (4) ◽  
pp. 361-363
Author(s):  
Toshio Yoshimura ◽  
Masanori Kiyota ◽  
Takashi Soeda
Keyword(s):  
Adaptive Control ◽  
Feedback Control ◽  
Linear Systems ◽  
Discrete Time ◽  
Control Policy ◽  
Optimal Feedback Control ◽  
Random Parameters ◽  
Control Cost ◽  
Simulation Results ◽  
Time Linear

An adaptive control policy of discrete-time linear systems with random parameters under a quadratic control cost function is treated. The policy is mainly based on the concept of one-measurement optimal feedback control. Simulation results indicate that the proposed method is superior to the certainty equivalence control.

Sign in / Sign up

Export Citation Format

Share Document